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

    Neuronpedia

    INDEX
    Explanations

    number and unit specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.95
    ad
    0.93
    ב
    0.88
     at
    0.84
     to
    0.82
    in
    0.80
    is
    0.79
    ס
    0.79
    en
    0.78
     of
    0.77
    POSITIVE LOGITS
     risposta
    0.71
     esimerk
    0.67
     hindrance
    0.66
     preparación
    0.65
     regimen
    0.65
     conexión
    0.65
     flowchart
    0.64
    ման
    0.64
     destrucción
    0.64
    он
    0.63
    Act Density 0.123%

    No Known Activations