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

    Neuronpedia

    INDEX
    Explanations

    api calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     datasets
    0.44
     obiekt
    0.42
     করছে
    0.41
     змо
    0.41
     oggetto
    0.40
     contiene
    0.40
     anno
    0.40
     zrobi
    0.39
     Server
    0.39
     играет
    0.39
    POSITIVE LOGITS
    hado
    0.42
    physiological
    0.41
    揾
    0.38
    effort
    0.38
    how
    0.37
    passage
    0.37
    blanc
    0.37
    hood
    0.36
    канчи
    0.36
    appropri
    0.35
    Act Density 0.001%

    No Known Activations