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

    Neuronpedia

    INDEX
    Explanations

    characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珽
    0.46
    ণাস্ত্র
    0.45
     apellidos
    0.44
    dwyd
    0.41
    滘
    0.38
    បទ
    0.38
    ဿ
    0.38
    Apellido
    0.38
     آئینے
    0.37
    <bbox>
    0.37
    POSITIVE LOGITS
     char
    3.39
    char
    3.25
    Char
    3.19
     Char
    3.09
    CHAR
    2.84
     CHAR
    2.81
     character
    2.78
     Character
    2.70
    Character
    2.66
    character
    2.66
    Act Density 0.166%

    No Known Activations