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

    Neuronpedia

    INDEX
    Explanations

    UD

    np_max-act · gemini-2.0-flash

    This neuron fires on technical acronyms, abbreviations, and other specialized labels—especially the parts of hyphenated or compound terms (e.g. “HUD,” “α3,” “mpMRI,” “LCOS-SLM”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sill
    -0.07
    hill
    -0.07
     wound
    -0.06
     FLAG
    -0.06
     upstream
    -0.06
    PAL
    -0.06
     superhero
    -0.06
     hover
    -0.06
     rituals
    -0.06
    DVD
    -0.06
    POSITIVE LOGITS
    鼻
    0.07
     Brow
    0.07
    ใบ
    0.07
     اظ
    0.07
    +c
    0.07
    �
    0.07
    -'.$
    0.07
    □□
    0.06
    ข
    0.06
    α
    0.06
    Act Density 0.164%

    No Known Activations