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

    Neuronpedia

    INDEX
    Explanations

    introducing lists or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     him
    0.77
     \...
    0.74
    \_
    0.72
     worded
    0.69
    🕙
    0.69
    ,
    0.68
    ,\"
    0.67
     প্রমুখ
    0.66
    \...
    0.64
    \",
    0.64
    POSITIVE LOGITS
     There
    1.66
     Examples
    1.60
     Consider
    1.59
     Including
    1.57
     Specifically
    1.55
     Often
    1.54
     Các
    1.54
     Includes
    1.51
     Notably
    1.48
     Depending
    1.46
    Act Density 0.656%

    No Known Activations