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

    Neuronpedia

    INDEX
    Explanations

    <body> or ```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.55
    ’
    0.49
    ంట్
    0.45
    Ꮏ
    0.44
    هي
    0.43
    ната
    0.42
    حان
    0.42
    ↵
    0.42
    nın
    0.42
    әне
    0.42
    POSITIVE LOGITS
    of
    0.52
     の
    0.51
    alu
    0.50
    )\
    0.49
    ೦
    0.41
    }\
    0.41
    もの
    0.41
     जून
    0.41
     तोड़
    0.40
    (
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.