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

    Neuronpedia

    INDEX
    Explanations

    common pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Morfo
    -0.85
    鉦
    -0.84
    hskip
    -0.81
     yearly
    -0.81
     finition
    -0.81
     phenomenal
    -0.79
     swiftly
    -0.77
    ടെ
    -0.77
     plead
    -0.76
    魔兽
    -0.76
    POSITIVE LOGITS
     　　
    0.99
    Provide
    0.91
    래스
    0.90
     และ
    0.90
    addListener
    0.90
     Coppola
    0.88
    はまだ
    0.87
    νες
    0.87
    ⅰ
    0.86
     prodotti
    0.85
    Act Density 0.003%

    No Known Activations