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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wounded
    -0.07
    ời
    -0.07
     stk
    -0.07
     onChangeText
    -0.07
    .tel
    -0.07
    omite
    -0.07
    빌
    -0.06
    瀬
    -0.06
     broadly
    -0.06
     routes
    -0.06
    POSITIVE LOGITS
     forKey
    0.07
     Monument
    0.07
     kim
    0.07
     nond
    0.07
    _ratings
    0.06
     Attribution
    0.06
    atro
    0.06
    咲
    0.06
     handbook
    0.06
    ESH
    0.06
    Act Density 0.139%

    No Known Activations