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

    Neuronpedia

    INDEX
    Explanations

    masculinity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drifting
    -0.08
     cyber
    -0.07
     Zen
    -0.07
     Frozen
    -0.06
     Россия
    -0.06
     urinary
    -0.05
     Drum
    -0.05
     fatty
    -0.05
    احة
    -0.05
     Σύ
    -0.05
    POSITIVE LOGITS
     swaps
    0.08
    asp
    0.07
    pellier
    0.07
    ?"↵
    0.07
     novamente
    0.07
     Lebanon
    0.07
     horm
    0.06
    Ev
    0.06
    [,
    0.06
     specifics
    0.06
    Act Density 0.000%

    No Known Activations