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

    Neuronpedia

    INDEX
    Explanations

    although

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inform
    -0.88
    wisdom
    -0.84
     wisdom
    -0.79
    ReusableCell
    -0.73
    insights
    -0.71
     insight
    -0.70
     insights
    -0.68
    o
    -0.65
     troops
    -0.65
     army
    -0.64
    POSITIVE LOGITS
     Monfieur
    0.70
     Shakspeare
    0.68
    <bos>
    0.65
    mybatisplus
    0.65
     nahilalakip
    0.63
     disambiguazione
    0.61
     uſed
    0.61
     raiſ
    0.61
     becauſe
    0.59
     neceffary
    0.58
    Act Density 0.300%

    No Known Activations