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

    Neuronpedia

    INDEX
    Explanations

    call to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ными
    0.96
    нием
    0.96
    ślin
    0.94
    েরই
    0.93
     पड़ता
    0.88
    p
    0.88
    ள்
    0.87
    ה
    0.86
    ओं
    0.86
     mismo
    0.85
    POSITIVE LOGITS
    electronics
    0.85
    0.82
    methylation
    0.79
     emailed
    0.79
    electronic
    0.77
     edited
    0.75
     अशोक
    0.74
     hacked
    0.73
     appr
    0.71
     gpointer
    0.71
    Act Density 0.000%

    No Known Activations