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

    Neuronpedia

    INDEX
    Explanations

    fair coin or die

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bloco
    0.64
    ].
    0.60
    </b>
    0.57
     خواتین
    0.57
    ilizce
    0.54
    }.
    0.52
    Ns
    0.52
     moms
    0.51
     Conselho
    0.51
     GoName
    0.50
    POSITIVE LOGITS
    am
    0.62
    ール
    0.61
    ိတ်
    0.61
     a
    0.59
    ול
    0.57
    тата
    0.57
    sley
    0.56
    대전
    0.55
    um
    0.55
    क
    0.55
    Act Density 0.001%

    No Known Activations