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

    Neuronpedia

    INDEX
    Explanations

    Saying something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     הדין
    -0.07
    .setFill
    -0.07
     tuition
    -0.07
    /C
    -0.07
    coc
    -0.07
    未经
    -0.06
    مق
    -0.06
     ,↵↵
    -0.06
    볕
    -0.06
    商标
    -0.06
    POSITIVE LOGITS
    折扣
    0.08
     impacts
    0.07
    OutOf
    0.07
    _evaluation
    0.07
     boosted
    0.07
     dần
    0.07
    POOL
    0.07
    Updates
    0.07
    .Book
    0.07
    巩固
    0.07
    Act Density 0.101%

    No Known Activations