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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abort
    -0.06
     ineff
    -0.06
    鼓
    -0.06
    Identification
    -0.06
     Promotion
    -0.06
    -author
    -0.06
    utton
    -0.06
    σμό
    -0.06
    director
    -0.06
     kolem
    -0.06
    POSITIVE LOGITS
    omal
    0.06
    peek
    0.06
    _bin
    0.06
     Accuracy
    0.06
     dislikes
    0.06
    дя
    0.06
    ば
    0.06
    =params
    0.06
     pData
    0.06
    .getBounds
    0.06
    Act Density 0.028%

    No Known Activations