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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on CamelCase identifiers—especially class or constructor names in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ミ
    -0.07
     خلال
    -0.07
    ken
    -0.06
     convoy
    -0.06
    crear
    -0.06
    .Add
    -0.06
    buf
    -0.06
    hari
    -0.06
    Ol
    -0.06
    _help
    -0.06
    POSITIVE LOGITS
     venues
    0.07
    =back
    0.07
     نادي
    0.07
     있던
    0.07
     softmax
    0.07
    -native
    0.06
     okamž
    0.06
    /|
    0.06
     درصد
    0.06
     الاح
    0.06
    Act Density 0.044%

    No Known Activations