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

    Neuronpedia

    INDEX
    Explanations

    Names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    0.98
    憬
    0.89
     nth
    0.88
    ாதி
    0.87
    ্তির
    0.85
    elier
    0.84
    ikums
    0.83
    czy
    0.83
    ttet
    0.82
    adır
    0.81
    POSITIVE LOGITS
    )،
    1.14
     and
    1.11
    ),
    1.05
    )、
    1.02
    ).\
    0.98
    )。
    0.94
    、​
    0.92
     Análisis
    0.92
     Lemma
    0.91
    \
    0.91
    Act Density 0.051%

    No Known Activations