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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lec
    0.78
    keV
    0.72
    jenje
    0.71
    jed
    0.70
    endip
    0.70
    Hora
    0.69
    Setpoint
    0.68
    Sigma
    0.68
    urup
    0.67
    ccak
    0.67
    POSITIVE LOGITS
     "
    1.20
     "...
    1.02
     "[
    1.01
     ".
    1.00
     "?
    0.99
    "
    0.97
     "(
    0.97
     ""
    0.97
     "_
    0.95
    "?
    0.94
    Act Density 0.000%

    No Known Activations