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

    Neuronpedia

    INDEX
    Explanations

    become: for privilege

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ကြာ
    0.40
     COLLATION
    0.39
    millan
    0.39
    磪
    0.38
    umur
    0.37
    alignat
    0.37
     Revised
    0.36
    }\|_{
    0.35
    衵
    0.35
    زه
    0.35
    POSITIVE LOGITS
    begin
    0.57
     Begin
    0.57
     Be
    0.54
     Begins
    0.54
    Be
    0.53
     Бе
    0.52
     beginning
    0.52
     Beginn
    0.50
     Beagle
    0.49
     Beginning
    0.49
    Act Density 0.001%

    No Known Activations