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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron activates on programming‐and concurrency‐related tokens—especially threading and synchronization constructs (e.g. thread, mutex/lock, condition_variable, Producer/Consumer patterns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     homosex
    -0.07
    �
    -0.06
    .records
    -0.06
     Linden
    -0.06
     nickel
    -0.06
     ThreadPool
    -0.06
     NPC
    -0.06
     bodies
    -0.06
     odd
    -0.06
     letzten
    -0.06
    POSITIVE LOGITS
     зрения
    0.07
    eresa
    0.07
    bucks
    0.06
     Крас
    0.06
    sar
    0.06
    lifting
    0.06
    LOTS
    0.06
    �
    0.06
    .onPause
    0.06
    ью
    0.06
    Act Density 0.015%

    No Known Activations