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

    Neuronpedia

    INDEX
    Explanations

    .jpg file extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $('
    0.84
    ъем
    0.79
    ríklad
    0.78
    arist
    0.77
    as
    0.77
    ר
    0.75
    र्
    0.75
    ักษณ์
    0.73
    ricult
    0.72
     നിങ്ങൾ
    0.71
    POSITIVE LOGITS
    ))
    1.06
    обходимо
    1.00
    );
    0.98
    смотря
    0.93
    )]
    0.93
    まあ
    0.88
    )
    0.87
    ).
    0.87
    oretically
    0.85
    हिट
    0.83
    Act Density 0.352%

    No Known Activations