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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    专项
    -0.09
     combater
    -0.09
     Libraries
    -0.08
     subsidies
    -0.08
    ශ
    -0.08
    ERGY
    -0.08
     бақыла
    -0.08
     subsid
    -0.08
     classify
    -0.08
     מגוון
    -0.08
    POSITIVE LOGITS
     Nurse
    0.09
     clicked
    0.09
     inesper
    0.08
     उसने
    0.08
    ُ
    0.08
    _inner
    0.08
     Wife
    0.08
    _clicked
    0.08
     Britney
    0.08
    _party
    0.08
    Act Density 0.039%

    No Known Activations