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

    Neuronpedia

    INDEX
    Explanations

    words related to lists or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၻ
    0.94
    ၷ
    0.87
    Its
    0.84
    ﾕ
    0.82
    Thats
    0.82
    Otros
    0.82
    Those
    0.80
    0.78
    Others
    0.77
    ්‍
    0.77
    POSITIVE LOGITS
     pygame
    0.47
     jest
    0.46
     Shuffle
    0.46
     Mathf
    0.44
     the
    0.42
     Weather
    0.40
     Newtonsoft
    0.39
     Arabidopsis
    0.39
     a
    0.39
    的
    0.39
    Act Density 7.885%

    No Known Activations