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

    Neuronpedia

    INDEX
    Explanations

    accented by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.75
    ist
    0.68
    nian
    0.65
     हज़ार
    0.63
    el
    0.61
    étrico
    0.61
    5
    0.61
    ag
    0.60
    går
    0.60
     Fuer
    0.60
    POSITIVE LOGITS
    Voici
    0.70
    逖
    0.69
    רו
    0.67
    י
    0.66
    ב
    0.64
    \
    0.64
    ي
    0.61
    מ
    0.57
     STATE
    0.57
    ש
    0.57
    Act Density 0.000%

    No Known Activations