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

    Neuronpedia

    INDEX
    Explanations

    newly capitalized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    もない
    -0.78
    ndez
    -0.76
    ndor
    -0.75
    ﾟ)
    -0.74
    Klar
    -0.73
    SaveChangesAsync
    -0.73
    ຍ
    -0.73
    andidate
    -0.72
    まれ
    -0.71
    isdir
    -0.71
    POSITIVE LOGITS
     Howell
    0.82
     []*
    0.77
    蔣
    0.72
    GLUT
    0.71
    Timings
    0.71
    湖
    0.70
    环
    0.69
    éfonos
    0.69
    Οι
    0.68
     hagy
    0.67
    Act Density 0.076%

    No Known Activations