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

    Neuronpedia

    INDEX
    Explanations

    Programming functions and variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    トラブル
    -0.08
    ビル
    -0.08
    Transformation
    -0.08
    Enter
    -0.07
    Allocator
    -0.07
     الفريق
    -0.07
     squirt
    -0.07
    inerary
    -0.07
     breakup
    -0.07
    路线
    -0.07
    POSITIVE LOGITS
    �
    0.07
    (seconds
    0.07
    很差
    0.07
    诩
    0.07
     preceded
    0.07
     xl
    0.07
     проц
    0.06
     repent
    0.06
    <()>
    0.06
    ...]
    0.06
    Act Density 0.019%

    No Known Activations