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

    Neuronpedia

    INDEX
    Explanations

    sexual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𬳶
    -0.07
    钢
    -0.07
    <Component
    -0.07
    坒
    -0.07
    explicit
    -0.07
    京
    -0.07
    _INSTANCE
    -0.07
     Evening
    -0.07
    liğ
    -0.07
     pouco
    -0.07
    POSITIVE LOGITS
     ESA
    0.08
     dabei
    0.07
     hits
    0.07
    窒息
    0.07
     habitat
    0.07
    kiye
    0.07
    ua
    0.07
    かもしれ
    0.07
    phot
    0.07
     varied
    0.07
    Act Density 0.015%

    No Known Activations