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

    Neuronpedia

    INDEX
    Explanations

    org/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िन
    0.48
    ِين
    0.47
    ాత
    0.44
    న్
    0.44
    illées
    0.43
    }$.
    0.42
    一脸
    0.41
     Muhammadu
    0.41
     thermostats
    0.41
    ン
    0.41
    POSITIVE LOGITS
    ud
    0.54
    '
    0.53
    ۰
    0.51
    th
    0.45
     sibling
    0.44
    ink
    0.42
    ian
    0.42
    5
    0.42
    ant
    0.41
    id
    0.41
    Act Density 0.001%

    No Known Activations