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

    Neuronpedia

    INDEX
    Explanations

    financing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     descent
    0.73
    ساب
    0.73
    Specifically
    0.69
    с
    0.66
    이가
    0.65
     noted
    0.64
     specifically
    0.64
    行く
    0.64
    aket
    0.64
    ى
    0.64
    POSITIVE LOGITS
     Führung
    0.91
     Muit
    0.88
     Debi
    0.84
     Puja
    0.82
     înviat
    0.82
     médicas
    0.81
    ॐ
    0.81
     Máy
    0.80
     Duss
    0.80
    𝑧
    0.79
    Act Density 0.000%

    No Known Activations