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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.11
    .↵
    -0.09
    .↵↵
    -0.09
    .
↵
    -0.08
     Bach
    -0.07
    。↵
    -0.07
    as
    -0.07
    umber
    -0.07
    رون
    -0.07
     choses
    -0.07
    POSITIVE LOGITS
    (Block
    0.07
    Though
    0.07
    mont
    0.07
     лит
    0.07
    .ua
    0.07
    维权
    0.07
    خل
    0.07
    semantic
    0.07
     uğra
    0.07
    Hopefully
    0.07
    Act Density 0.888%

    No Known Activations