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

    Neuronpedia

    INDEX
    Explanations

    excess fluids, weight, mucus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    2.55
    ا
    2.27
    ం
    2.03
    𝙎
    1.91
    い
    1.82
    스를
    1.74
    и
    1.71
    ε
    1.70
    𝕊
    1.70
    客様
    1.69
    POSITIVE LOGITS
    hesized
    1.93
    ae
    1.88
    ist
    1.86
     tôt
    1.82
    es
    1.76
    m
    1.76
    aan
    1.73
    dır
    1.71
    ud
    1.70
    Ι
    1.70
    Act Density 0.002%

    No Known Activations