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

    Neuronpedia

    INDEX
    Explanations

    prompt context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.68
    udi
    0.62
    ,
    0.58
     within
    0.55
    astro
    0.53
     for
    0.52
    oko
    0.52
    unga
    0.52
    for
    0.51
     around
    0.51
    POSITIVE LOGITS
     Зак
    0.65
     Maßnahmen
    0.63
     აქ
    0.61
     Evaluación
    0.57
    िकेटेड
    0.55
    roffenen
    0.55
     ACTIVITIES
    0.55
     टास्क
    0.55
    Პ
    0.55
    GetAll
    0.54
    Act Density 0.000%

    No Known Activations