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

    Neuronpedia

    INDEX
    Explanations

    shade, blinds, task, lambda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    веде
    0.50
     calculating
    0.48
     heterod
    0.47
     danam
    0.46
     conjugate
    0.45
     મોત
    0.45
     heady
    0.45
     whitish
    0.45
     crystallization
    0.44
    Ⓒ
    0.43
    POSITIVE LOGITS
    <0x0D>
    0.49
     QS
    0.48
    peak
    0.47
    '
    0.47
    </td>
    0.46
    PORT
    0.45
     (
    0.42
    St
    0.42
    Many
    0.42
     zaman
    0.42
    Act Density 0.000%

    No Known Activations