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

    Neuronpedia

    INDEX
    Explanations

    Peace

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pieces
    0.72
     zer
    0.67
    msp
    0.66
     piece
    0.64
    periodic
    0.63
    istä
    0.62
    sley
    0.61
     அல
    0.61
     lifes
    0.61
     взял
    0.61
    POSITIVE LOGITS
    eworthy
    0.75
    Park
    0.73
     Maker
    0.69
     อย่าง
    0.69
    Talk
    0.68
     singoli
    0.68
    akoti
    0.67
    خواه
    0.67
    χω
    0.66
    טי
    0.66
    Act Density 0.008%

    No Known Activations