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

    Neuronpedia

    INDEX
    Explanations

    pleasure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accomplishment
    -0.07
    Draft
    -0.06
    ث
    -0.06
    .der
    -0.06
     дра
    -0.06
     návrh
    -0.06
    /rc
    -0.05
    Exp
    -0.05
     없었다
    -0.05
     obs
    -0.05
    POSITIVE LOGITS
    ública
    0.07
    EditingController
    0.07
    ISTICS
    0.06
    0.06
    .decode
    0.06
     brightness
    0.06
     Öz
    0.06
    etros
    0.06
    _SIG
    0.06
    収
    0.06
    Act Density 0.075%

    No Known Activations