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

    Neuronpedia

    INDEX
    Explanations

    negation, lack, or difficulty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поча
    0.59
     risorse
    0.54
     recursos
    0.54
     подготовке
    0.53
     preparazione
    0.53
     ресурсов
    0.51
     ресур
    0.51
     ресурсы
    0.51
    кость
    0.50
    ષા
    0.50
    POSITIVE LOGITS
     coin
    0.55
     automobile
    0.53
     swimmer
    0.50
     IL
    0.48
     of
    0.46
     ordinary
    0.46
     US
    0.46
    .
    0.46
     oath
    0.45
     el
    0.45
    Act Density 0.001%

    No Known Activations