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

    Neuronpedia

    INDEX
    Explanations

    quantity subtraction or addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    হাট
    0.42
    óloga
    0.41
    échelle
    0.41
     вигляді
    0.38
    óz
    0.38
    Bew
    0.38
    Př
    0.38
     oce
    0.38
    nên
    0.37
    ύ
    0.36
    POSITIVE LOGITS
     simply
    0.43
     simpel
    0.40
     simplemente
    0.38
     simplement
    0.37
    どのように
    0.37
     semplicemente
    0.36
     இருப்பது
    0.36
     просто
    0.35
    一日
    0.33
    无论
    0.33
    Act Density 0.001%

    No Known Activations