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

    Neuronpedia

    INDEX
    Explanations

    `.then(data => {`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tera
    1.04
    Collision
    1.02
    lal
    0.99
    hearted
    0.98
    tob
    0.96
    Tp
    0.95
    r
    0.92
     মতি
    0.92
     collage
    0.92
    蜓
    0.90
    POSITIVE LOGITS
    zeń
    1.09
    Wow
    0.99
     ciudadanos
    0.97
    نگی
    0.96
    fähig
    0.96
     reservar
    0.95
     aDict
    0.95
     fomentar
    0.95
     pela
    0.95
     göt
    0.93
    Act Density 0.001%

    No Known Activations