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

    Neuronpedia

    INDEX
    Explanations

    icon and outline properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.78
     on
    0.68
     $
    0.65
    ↵↵
    0.63
     AT
    0.61
    dan
    0.61
     s
    0.57
    ears
    0.57
    eker
    0.57
     a
    0.56
    POSITIVE LOGITS
    ಲ
    0.71
    σα
    0.70
    يو
    0.68
    inFile
    0.67
     Queste
    0.67
     permitido
    0.66
    νό
    0.66
    "/"
    0.66
    пада
    0.65
    -{
    0.65
    Act Density 0.000%

    No Known Activations