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

    Neuronpedia

    INDEX
    Explanations

    oric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wasn
    -0.89
    fue
    -0.82
     Wasn
    -0.82
    Was
    -0.81
     was
    -0.80
    wasn
    -0.80
    was
    -0.79
     Was
    -0.79
    Fue
    -0.72
     Fue
    -0.71
    POSITIVE LOGITS
    脚注の使い方
    0.73
    Rüyada
    0.68
    0.66
    MessageOf
    0.63
    abestanden
    0.62
    الدراسه
    0.62
    FundMe
    0.60
    owulf
    0.59
    ⓘ
    0.59
     localObject
    0.58
    Act Density 0.099%

    No Known Activations