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

    Neuronpedia

    INDEX
    Explanations

    Arabic 'sh' prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irmat
    0.42
    kuu
    0.39
    ouri
    0.39
    feira
    0.39
    aurus
    0.38
    ickers
    0.38
     abbrevi
    0.38
    sak
    0.36
    appid
    0.36
    hj
    0.36
    POSITIVE LOGITS
    Tangent
    0.41
    Scape
    0.41
     nin
    0.40
    తా
    0.40
    ratings
    0.40
    Selon
    0.40
    HOLD
    0.39
    Executive
    0.39
    عبة
    0.39
    評
    0.39
    Act Density 0.001%

    No Known Activations