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

    Neuronpedia

    INDEX
    Explanations

    masculinity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FDA
    -0.07
     Rib
    -0.07
     oss
    -0.06
    (\$
    -0.06
     lament
    -0.06
     ents
    -0.06
     primo
    -0.06
     Ann
    -0.06
    anford
    -0.06
    ório
    -0.06
    POSITIVE LOGITS
    paque
    0.07
    .real
    0.07
    .country
    0.07
    .take
    0.07
     Opcode
    0.06
     Sebast
    0.06
     INTERRU
    0.06
    kea
    0.06
     František
    0.06
     blade
    0.06
    Act Density 0.002%

    No Known Activations