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

    Neuronpedia

    INDEX
    Explanations

    image descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hypnotic
    0.42
     idempotent
    0.42
    ዦ
    0.41
     nilpotent
    0.40
    plicial
    0.38
     slip
    0.37
    ករណ៍
    0.37
     substrate
    0.36
     sixth
    0.36
     endogenous
    0.36
    POSITIVE LOGITS
    Photo
    0.69
    Foto
    0.61
    photo
    0.59
    Фото
    0.58
    Пре
    0.57
    Пред
    0.56
    Công
    0.56
    При
    0.55
    Не
    0.55
    Если
    0.55
    Act Density 0.000%

    No Known Activations