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

    Neuronpedia

    INDEX
    Explanations

    specifying output format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.11
    ໃນ
    0.74
    ,
    0.68
    在
    0.67
     در
    0.65
    ใน
    0.64
    ה
    0.63
    ים
    0.63
    ;
    0.62
     by
    0.61
    POSITIVE LOGITS
    格式
    1.17
    Format
    1.09
     Format
    1.05
     formatos
    1.03
    format
    0.97
     формат
    0.97
    Formatting
    0.95
     FORMAT
    0.92
     फॉर्मेट
    0.92
     formats
    0.89
    Act Density 0.039%

    No Known Activations