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

    Neuronpedia

    INDEX
    Explanations

    anonymized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flutter
    0.40
     Vide
    0.39
     জায়
    0.38
     ▶
    0.37
    Vide
    0.37
     Zo
    0.36
     حين
    0.36
    كلات
    0.36
     saat
    0.36
    outch
    0.36
    POSITIVE LOGITS
    Anonymous
    0.86
     Anonymous
    0.86
     anonymous
    0.86
     anon
    0.77
    anonymous
    0.75
     anonymity
    0.75
    匿名
    0.74
     anonymously
    0.70
     Anon
    0.66
    Anon
    0.66
    Act Density 0.000%

    No Known Activations