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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yayım
    -0.07
     inadvertently
    -0.07
    황
    -0.07
    }",
    -0.07
    manifest
    -0.06
    司
    -0.06
    恨
    -0.06
    christ
    -0.06
    _fraction
    -0.06
    weg
    -0.06
    POSITIVE LOGITS
    台灣
    0.06
     POL
    0.06
     não
    0.06
     결
    0.06
    اطل
    0.06
     sector
    0.05
     nhiêu
    0.05
    createQuery
    0.05
     ні
    0.05
     utilis
    0.05
    Act Density 0.000%

    No Known Activations