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

    Neuronpedia

    INDEX
    Explanations

    checking in and out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h2>
    0.75
    <0x0D>
    0.75
    </b>
    0.65
    </h4>
    0.64
    ;
    0.64
    </strong>
    0.63
     recorr
    0.62
    _
    0.61
    </th>
    0.61
    </u>
    0.61
    POSITIVE LOGITS
    Check
    0.77
     on
    0.71
    ב
    0.71
     チェック
    0.71
     Check
    0.70
    CHEC
    0.70
     checkpoints
    0.70
     체크
    0.70
    CHECK
    0.70
     наличие
    0.70
    Act Density 0.108%

    No Known Activations