Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash

    elements related to build systems and file configurations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires strongest on directory‐path and build‐directory variable references (e.g. “../”, “top_src_dir”, “dir”) in Makefiles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     protesting
    -0.07
     Brave
    -0.06
    npc
    -0.06
    ICIENT
    -0.06
     resilient
    -0.06
     Zac
    -0.06
    NPC
    -0.06
     intend
    -0.06
     persone
    -0.06
    ocaust
    -0.06
    POSITIVE LOGITS
     adipiscing
    0.07
    	resolve
    0.07
     Daten
    0.07
    adioButton
    0.06
     तरफ
    0.06
    .Sound
    0.06
     اصل
    0.06
     علاوه
    0.06
    _ENUM
    0.06
    :[↵
    0.06
    Act Density 0.004%

    No Known Activations