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

    Neuronpedia

    INDEX
    Explanations

    swap reverses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...
    0.49
     *
    0.44
    ⋅
    0.38
     sometimes
    0.38
    ....
    0.37
    Constit
    0.37
     **
    0.37
    <
    0.36
    **
    0.36
    dioxide
    0.36
    POSITIVE LOGITS
    成功的
    0.43
    nless
    0.40
     Ninth
    0.39
    ールの
    0.38
     শরীরের
    0.38
    㥆
    0.38
    叁章
    0.37
     bibliographic
    0.37
     మండల
    0.37
    ＮＡＮＡ
    0.36
    Act Density 0.001%

    No Known Activations