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

    Neuronpedia

    INDEX
    Explanations

    API and endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मजबूत
    0.38
    :].
    0.38
     نر
    0.36
    طيب
    0.36
    ಿದ್ದು
    0.35
    벡
    0.35
     helpers
    0.35
    ਟ
    0.35
    บริ
    0.35
     lil
    0.35
    POSITIVE LOGITS
     Fox
    0.44
     Prefer
    0.39
    ဤ
    0.38
     lijst
    0.38
     preferable
    0.37
     fox
    0.36
     najlepiej
    0.36
     liste
    0.36
    Fox
    0.36
     Cómo
    0.36
    Act Density 0.002%

    No Known Activations