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

    Neuronpedia

    INDEX
    Explanations

    Slavic word parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clazz
    0.63
    ccd
    0.59
     Spencer
    0.59
    嚐
    0.59
     insights
    0.57
    ஸின்
    0.55
     IONS
    0.55
    IONS
    0.54
    ions
    0.53
    ையே
    0.53
    POSITIVE LOGITS
    ровке
    0.89
    ровку
    0.88
    ówka
    0.88
    ровка
    0.80
    ровки
    0.76
    ровкой
    0.75
    ówki
    0.71
    тово
    0.68
    рово
    0.68
    ovní
    0.64
    Act Density 0.000%

    No Known Activations