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

    Neuronpedia

    INDEX
    Explanations

    python code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $)$.
    0.97
    .").
    0.86
    .',
    0.81
    .”.
    0.80
    .".
    0.80
    ?”.
    0.78
    \".
    0.77
    ’).
    0.77
    .’’
    0.76
    ."),
    0.76
    POSITIVE LOGITS
    </strong>
    0.96
    ↵
    0.85
     Your
    0.85
     Let
    0.84
    ↵↵
    0.84
    您的
    0.76
     Най
    0.72
                                   
    0.71
     |
    0.70
    </span>
    0.69
    Act Density 0.222%

    No Known Activations