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

    Neuronpedia

    INDEX
    Explanations

    state of completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тся
    1.15
    áculo
    1.01
    ০০
    0.98
     Среди
    0.96
    سٹم
    0.94
    IDADE
    0.93
     การ
    0.90
     Validación
    0.89
    ಿಕ
    0.89
    schutz
    0.88
    POSITIVE LOGITS
    and
    1.16
    .
    1.09
     and
    0.97
    ov
    0.89
    ont
    0.89
    he
    0.88
    urt
    0.86
    ast
    0.86
    .\\
    0.84
     pamphlets
    0.84
    Act Density 0.554%

    No Known Activations