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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愤
    -0.09
     rodz
    -0.07
    getting
    -0.07
     Sid
    -0.07
     COMM
    -0.07
    laughs
    -0.07
     tart
    -0.07
     Tháng
    -0.07
    iley
    -0.06
    características
    -0.06
    POSITIVE LOGITS
     Morgan
    0.08
    โหล
    0.07
    潜能
    0.07
    🔗
    0.07
    .Logf
    0.06
    スキ
    0.06
    评估
    0.06
    ◅
    0.06
     Franken
    0.06
     yapılan
    0.06
    Act Density 0.000%

    No Known Activations