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

    Neuronpedia

    INDEX
    Explanations

    I am/have/cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.67
    l
    0.65
    I
    0.61
    ات
    0.60
    s
    0.56
    ли
    0.56
    AK
    0.56
    n
    0.52
    و
    0.52
    other
    0.52
    POSITIVE LOGITS
     discovered
    0.49
     turbulence
    0.49
     discovers
    0.48
     devoured
    0.46
     attract
    0.46
     hadron
    0.46
     confronts
    0.45
     detects
    0.45
     cryogenic
    0.45
     polymorphic
    0.45
    Act Density 0.258%

    No Known Activations