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

    Neuronpedia

    INDEX
    Explanations

    python math nn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Compose
    0.70
    ubert
    0.66
    災害
    0.64
    બે
    0.63
     Nutzen
    0.63
    形態
    0.62
    form
    0.61
     Technische
    0.61
     Post
    0.61
    icoli
    0.61
    POSITIVE LOGITS
    ೊಂಡ
    0.73
    নকে
    0.72
    ivating
    0.72
     ấy
    0.71
     тот
    0.70
    inding
    0.70
     угро
    0.70
    īd
    0.70
     محکمہ
    0.70
     стран
    0.69
    Act Density 0.000%

    No Known Activations