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

    Neuronpedia

    INDEX
    Explanations

    prompt and generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    valve
    0.45
     VALVE
    0.45
    bolos
    0.41
     thereon
    0.38
    oyi
    0.38
    に入れる
    0.37
    餐
    0.37
    riages
    0.37
    ္
    0.36
     ballast
    0.36
    POSITIVE LOGITS
     schermo
    0.47
     onderwerp
    0.46
     viento
    0.45
     comparaison
    0.45
    丝毫
    0.45
     niente
    0.45
    owania
    0.44
     cœur
    0.44
     വ്യക്ത
    0.44
    比较
    0.43
    Act Density 0.003%

    No Known Activations