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

    Neuronpedia

    INDEX
    Explanations

    model (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    0.50
     other
    0.50
     only
    0.47
     each
    0.46
     even
    0.46
     cumulative
    0.46
     the
    0.46
     to
    0.45
     with
    0.45
    ated
    0.44
    POSITIVE LOGITS
     impasse
    0.70
    Yeah
    0.67
     resposta
    0.65
     réponses
    0.64
     odgovor
    0.63
     हाँ
    0.63
    ੈਂ
    0.63
    Resposta
    0.62
     respuesta
    0.62
    Wow
    0.61
    Act Density 1.989%

    No Known Activations