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

    Neuronpedia

    INDEX
    Explanations

    sexual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theory
    -0.07
     Finger
    -0.07
    .dumps
    -0.07
     emergency
    -0.06
    Pictures
    -0.06
     pain
    -0.06
    держ
    -0.06
     walnut
    -0.06
     Trojan
    -0.06
    -choice
    -0.06
    POSITIVE LOGITS
     etiquette
    0.06
    Once
    0.06
    větší
    0.06
     غ
    0.06
    틀
    0.06
    coc
    0.06
    <div
    0.06
    *r
    0.06
    .getSelectedItem
    0.06
    putc
    0.06
    Act Density 0.006%

    No Known Activations