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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    秭
    -0.07
    Evidence
    -0.07
     Overse
    -0.07
    依法
    -0.07
    �
    -0.07
     kb
    -0.07
     mism
    -0.07
    😌
    -0.07
    .leave
    -0.07
    (job
    -0.07
    POSITIVE LOGITS
     Rating
    0.07
    分かる
    0.07
    とりあえず
    0.07
    褕
    0.07
     selection
    0.07
    obook
    0.07
     clock
    0.06
    삷
    0.06
     crisp
    0.06
    _RANGE
    0.06
    Act Density 0.001%

    No Known Activations