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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     messaging
    -0.06
     Cir
    -0.06
    TY
    -0.06
     skilled
    -0.06
    Someone
    -0.06
    Apis
    -0.06
    .shared
    -0.06
    times
    -0.06
     compact
    -0.06
     closure
    -0.06
    POSITIVE LOGITS
    _question
    0.08
     resultados
    0.08
     主
    0.08
    管理条例
    0.08
    讲座
    0.08
     lah
    0.07
    ROME
    0.07
    프로그램
    0.07
    stantial
    0.07
     frankfurt
    0.07
    Act Density 0.111%

    No Known Activations