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

    Neuronpedia

    INDEX
    Explanations

    /Library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riminal
    -0.07
    _ter
    -0.07
    gons
    -0.07
     controller
    -0.06
    евой
    -0.06
    _ends
    -0.06
     hel
    -0.06
     DOCUMENT
    -0.06
    ungan
    -0.06
     Supplements
    -0.06
    POSITIVE LOGITS
    ,’”
    0.07
    _FW
    0.06
    766
    0.06
     necesita
    0.06
     reperc
    0.06
     báo
    0.06
     offsetY
    0.06
     readily
    0.06
    "),"
    0.06
    bidden
    0.06
    Act Density 0.001%

    No Known Activations