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

    Neuronpedia

    INDEX
    Explanations

    dates and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     прибы
    -0.95
    낯
    -0.88
    vriende
    -0.88
     Viitattu
    -0.87
    urismo
    -0.87
    クタ
    -0.86
     daging
    -0.86
    OMAS
    -0.85
     diverted
    -0.82
     vinci
    -0.81
    POSITIVE LOGITS
     NUEVO
    0.91
    DESCRIPCIÓN
    0.85
    стройства
    0.82
    ските
    0.82
    levering
    0.81
    少なくとも
    0.81
     bart
    0.80
     Such
    0.80
    octanol
    0.80
    Préparation
    0.79
    Act Density 0.007%

    No Known Activations