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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    避开
    -0.07
    embro
    -0.07
    Ε
    -0.07
     spells
    -0.07
    曾經
    -0.07
    ieving
    -0.07
    _MAT
    -0.07
     Swe
    -0.07
    washer
    -0.07
     בנ
    -0.07
    POSITIVE LOGITS
    getService
    0.07
    九年
    0.07
    ɰ
    0.07
    ’:
    0.06
     accessed
    0.06
     eight
    0.06
     Thus
    0.06
     Woo
    0.06
    褕
    0.06
    .UI
    0.06
    Act Density 0.014%

    No Known Activations