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

    Neuronpedia

    INDEX
    Explanations

    icon

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    plementation
    0.67
     derivs
    0.67
    淏
    0.64
    arris
    0.63
    ഢ
    0.63
    ريض
    0.63
     ҳа
    0.63
     سره
    0.62
     CFA
    0.62
     humoral
    0.62
    POSITIVE LOGITS
     icon
    2.84
     icons
    2.81
     Icon
    2.72
    Icon
    2.67
     Icons
    2.63
     ikon
    2.57
    Icons
    2.56
    icon
    2.53
     ICON
    2.47
     iconos
    2.46
    Act Density 0.130%

    No Known Activations