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

    Neuronpedia

    INDEX
    Explanations

    trackpad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.70
    ством
    0.67
    ag
    0.63
     Gewer
    0.61
    OSPHER
    0.61
    OC
    0.60
    o
    0.60
    उचर
    0.60
    ли
    0.59
    وي
    0.59
    POSITIVE LOGITS
    裒
    0.63
     justices
    0.59
     menyatakan
    0.59
     scintill
    0.57
     архив
    0.57
    polarized
    0.57
     যাবতীয়
    0.55
    ਮ
    0.55
    谆
    0.55
     paramètres
    0.54
    Act Density 0.000%

    No Known Activations