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

    Neuronpedia

    INDEX
    Explanations

    actions concerning voters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     말미암
    1.01
    ال
    0.98
    ك
    0.96
    ט
    0.96
    ﺕ
    0.95
    вати
    0.95
    ியா
    0.93
    과
    0.93
    ج
    0.91
    ات
    0.90
    POSITIVE LOGITS
    ↵↵
    1.06
     Voters
    0.98
    ↵
    0.95
    ments
    0.95
    .
    0.93
    नंतर
    0.89
     voters
    0.88
     voter
    0.88
      
    0.87
    ized
    0.86
    Act Density 0.001%

    No Known Activations