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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.81
    IVEREF
    -0.79
     otomatig
    -0.79
     الرياضيه
    -0.79
     nahilalakip
    -0.73
    adaptiveStyles
    -0.69
    ViewFeatures
    -0.68
     EconPapers
    -0.67
    }{*}{
    -0.66
    }';
    -0.66
    POSITIVE LOGITS
    .
    0.52
     sensibili
    0.46
     stubborn
    0.43
    ữa
    0.41
     une
    0.40
    二是
    0.40
    お待ちしております
    0.40
     not
    0.40
     better
    0.39
     sensib
    0.39
    Act Density 0.008%

    No Known Activations