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

    Neuronpedia

    INDEX
    Explanations

    Coding context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     שני
    -0.07
    ريس
    -0.06
     patt
    -0.06
     Flores
    -0.06
    inside
    -0.06
    𝙡
    -0.06
    משל
    -0.06
    새
    -0.06
    ー
    -0.06
    ENDING
    -0.06
    POSITIVE LOGITS
    .features
    0.07
     Terr
    0.06
    锦
    0.06
     עצמ
    0.06
     temper
    0.06
    Enumeration
    0.06
    Authors
    0.06
    .toFixed
    0.06
    という
    0.06
    _m
    0.06
    Act Density 0.002%

    No Known Activations