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

    Neuronpedia

    INDEX
    Explanations

    R: followed by codes or descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.54
    3
    0.49
    1
    0.48
    5
    0.44
    2
    0.43
    കോ
    0.42
     Highlighter
    0.41
    9
    0.41
    6
    0.41
     highlighter
    0.40
    POSITIVE LOGITS
     يقوم
    0.42
    の為
    0.40
     행
    0.36
    myapplication
    0.36
     आपण
    0.36
    стями
    0.36
     istnieje
    0.36
     свою
    0.35
     futile
    0.35
    ModelAdmin
    0.35
    Act Density 0.001%

    No Known Activations