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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ter
    -0.56
    sed
    -0.54
     meng
    -0.49
    med
    -0.49
    bry
    -0.48
    re
    -0.47
     ter
    -0.47
    HasKey
    -0.46
    brill
    -0.46
    ⓧ
    -0.45
    POSITIVE LOGITS
    存于互联网档案馆
    0.65
    évaluateur
    0.64
    ."],
    0.63
    /**
    0.59
     مشين
    0.59
    eſt
    0.57
     tartalomajánló
    0.56
     itſelf
    0.56
     myſelf
    0.56
     aanv
    0.54
    Act Density 0.001%

    No Known Activations