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

    Neuronpedia

    INDEX
    Explanations

    Sex and bodily emissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iton
    -0.07
    장을
    -0.07
    Sur
    -0.06
    ávka
    -0.06
    software
    -0.06
    Containers
    -0.06
     말을
    -0.06
    alar
    -0.06
     teş
    -0.06
     TW
    -0.06
    POSITIVE LOGITS
    (KERN
    0.06
     �
    0.06
    _ph
    0.06
     působ
    0.06
    0.06
     ринку
    0.06
    (Debug
    0.06
    。',↵
    0.06
     Appalachian
    0.05
     flux
    0.05
    Act Density 0.011%

    No Known Activations