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

    Neuronpedia

    INDEX
    Explanations

    expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    인트
    -0.06
     Viv
    -0.06
     nextPage
    -0.06
     ecology
    -0.06
     retrieve
    -0.06
    ák
    -0.06
    prt
    -0.06
     sonst
    -0.06
    .googleapis
    -0.06
    _Height
    -0.06
    POSITIVE LOGITS
    ABSPATH
    0.07
     금
    0.07
     відсут
    0.07
     writ
    0.07
    -caret
    0.06
     TextAlign
    0.06
     Due
    0.06
     czę
    0.06
    _fire
    0.06
    费
    0.06
    Act Density 0.014%

    No Known Activations