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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     masturbation
    -0.08
    .exam
    -0.07
     dikke
    -0.07
    净土
    -0.07
    atype
    -0.07
     Picasso
    -0.07
    _tuples
    -0.07
    _update
    -0.07
     cracks
    -0.07
    حسن
    -0.07
    POSITIVE LOGITS
    🔤
    0.07
    SPATH
    0.07
    PEnd
    0.07
    登录
    0.07
    ConnectionString
    0.07
    _FieldOffsetTable
    0.07
     State
    0.07
    就不能
    0.06
    𝙶
    0.06
     actionable
    0.06
    Act Density 0.002%

    No Known Activations