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

    Neuronpedia

    INDEX
    Explanations

    breasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anian
    -0.07
     культу
    -0.06
    نش
    -0.06
     Sơn
    -0.06
    тра
    -0.06
    엘
    -0.06
     CharSequence
    -0.06
     smrti
    -0.06
    (gen
    -0.06
    /world
    -0.06
    POSITIVE LOGITS
     boobs
    0.11
     tits
    0.07
    \HttpFoundation
    0.07
     regul
    0.07
     หน
    0.07
     upfront
    0.07
     Professor
    0.06
    .abort
    0.06
     busty
    0.06
    oler
    0.06
    Act Density 0.006%

    No Known Activations