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

    Neuronpedia

    INDEX
    Explanations

    try or attempt actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ния
    0.28
    ва
    0.27
     shelters
    0.27
    نة
    0.26
    сили
    0.26
    nte
    0.25
     acerca
    0.25
    luğu
    0.25
    ة
    0.25
     về
    0.24
    POSITIVE LOGITS
     for
    0.35
    al
    0.32
    ↵↵
    0.28
    ar
    0.26
    หรับ
    0.25
    ل
    0.24
     with
    0.24
     They
    0.23
    with
    0.23
     For
    0.23
    Act Density 0.608%

    No Known Activations