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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valves
    -0.08
    urations
    -0.08
    -existing
    -0.08
    _most
    -0.08
     Stap
    -0.07
    ');"
    -0.07
    DOC
    -0.07
    chwitz
    -0.07
    xygen
    -0.07
     typical
    -0.07
    POSITIVE LOGITS
     performance
    0.07
    Ҭ
    0.07
    Ẻ
    0.07
     integrating
    0.07
     spaces
    0.07
     Media
    0.07
    솨
    0.07
    ⊘
    0.06
    넋
    0.06
    擾
    0.06
    Act Density 0.009%

    No Known Activations