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

    Neuronpedia

    INDEX
    Explanations

    example usage: or explanation:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사용자
    0.76
     Usage
    0.72
     ดังนั้น
    0.72
    '},
    0.72
     स्‍
    0.68
    ()];
    0.68
     তবে
    0.66
    '});
    0.65
     وليس
    0.63
     Plugin
    0.63
    POSITIVE LOGITS
    春夏
    0.74
    ában
    0.73
    म्मू
    0.71
    oudre
    0.71
    нены
    0.70
    dengan
    0.69
    rescences
    0.69
    ángulos
    0.68
    étaient
    0.68
    ínas
    0.68
    Act Density 0.214%

    No Known Activations