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

    Neuronpedia

    INDEX
    Explanations

    error handling in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     בצ
    0.85
    ois
    0.78
    يانة
    0.76
     menand
    0.74
    van
    0.73
     می‌شوند
    0.73
    ⇄
    0.73
    can
    0.73
    xi
    0.72
     erhält
    0.71
    POSITIVE LOGITS
    ático
    0.92
     Qualquer
    0.83
    áticas
    0.80
    acco
    0.78
    ática
    0.78
    isph
    0.75
     addTodo
    0.74
     Â
    0.74
    áticos
    0.73
    ú
    0.73
    Act Density 0.033%

    No Known Activations