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

    Neuronpedia

    INDEX
    Explanations

    other followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.57
    ’
    0.54
    ur
    0.52
    4
    0.49
    ist
    0.49
    。
    0.48
    OP
    0.48
    '
    0.48
     rutrum
    0.48
    _
    0.46
    POSITIVE LOGITS
    worldly
    0.56
    დას
    0.56
    h
    0.53
     türlü
    0.52
    方面的
    0.49
    ли
    0.47
    ј
    0.46
    もあった
    0.46
    d
    0.45
    بق
    0.45
    Act Density 0.102%

    No Known Activations