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

    Neuronpedia

    INDEX
    Explanations

    conjugated chemical and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {
    0.86
     at
    0.82
     for
    0.79
    Farland
    0.77
    Más
    0.76
    Einstellungen
    0.74
    D
    0.71
     of
    0.71
    OT
    0.71
    RE
    0.70
    POSITIVE LOGITS
    ی
    1.18
    т
    1.10
    ים
    0.95
    s
    0.93
    ्स
    0.93
    ή
    0.92
    та
    0.91
    ран
    0.89
    ओं
    0.88
    ก
    0.88
    Act Density 0.001%

    No Known Activations