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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    簡
    -0.07
    照
    -0.07
    rap
    -0.07
    _low
    -0.06
    .pagination
    -0.06
    เอก
    -0.06
     cessation
    -0.06
    ถ
    -0.06
     पड़
    -0.06
     impost
    -0.06
    POSITIVE LOGITS
     kz
    0.07
    stag
    0.06
    [↵
    0.06
     ।↵
    0.06
    Boot
    0.06
    َح
    0.06
     Bands
    0.06
    .concatenate
    0.06
    】↵
    0.06
     силь
    0.06
    Act Density 0.048%

    No Known Activations