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

    Neuronpedia

    INDEX
    Explanations

    identifiers or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theoretical
    0.73
    GoAbroad
    0.71
     Theoretical
    0.63
     Analog
    0.63
    PreviewSize
    0.62
    hapi
    0.61
    ጨም
    0.61
     best
    0.61
     Choosing
    0.60
     пита
    0.60
    POSITIVE LOGITS
    ak
    0.78
    un
    0.75
    ap
    0.75
    ash
    0.74
    ck
    0.74
    ub
    0.74
    ab
    0.74
    G
    0.71
    ruk
    0.71
    presidente
    0.71
    Act Density 0.216%

    No Known Activations