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

    Neuronpedia

    INDEX
    Explanations

    HEAD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [self
    -0.07
     Devices
    -0.07
    を迎
    -0.07
     dyn
    -0.07
     null
    -0.06
    <Expression
    -0.06
    _SUS
    -0.06
    .setColumn
    -0.06
    _OscInitStruct
    -0.06
     trả
    -0.06
    POSITIVE LOGITS
     sextreffen
    0.07
    ittal
    0.07
    く
    0.07
    flammatory
    0.07
     cheating
    0.07
    网址
    0.07
     Kw
    0.07
    _arrow
    0.07
    ooting
    0.07
    写字
    0.06
    Act Density 0.000%

    No Known Activations