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

    Neuronpedia

    INDEX
    Explanations

    1-800-656-HOPE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    picture
    0.39
    Weil
    0.38
     Arctic
    0.37
    Arctic
    0.37
     பிரதி
    0.35
     arctic
    0.35
    helper
    0.35
     Push
    0.35
     giai
    0.34
    honor
    0.34
    POSITIVE LOGITS
    빗
    0.39
    ствий
    0.38
     Edd
    0.38
     законом
    0.37
     issuance
    0.37
     Ed
    0.36
    तियां
    0.36
    лии
    0.36
    蚣
    0.36
     এড
    0.36
    Act Density 0.009%

    No Known Activations