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

    Neuronpedia

    INDEX
    Explanations

    interactive shell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    潇
    -0.07
     Police
    -0.07
    力量
    -0.07
    Field
    -0.07
     holder
    -0.07
     Coffee
    -0.06
     precursor
    -0.06
     Australia
    -0.06
    stream
    -0.06
    高职
    -0.06
    POSITIVE LOGITS
    .temp
    0.07
    ❱
    0.07
     безопас
    0.07
    /buttons
    0.07
    Verified
    0.06
    アク
    0.06
    شركات
    0.06
     משחקים
    0.06
     Kohana
    0.06
     khẳng
    0.06
    Act Density 0.040%

    No Known Activations