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

    Neuronpedia

    INDEX
    Explanations

    romance/sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getS
    -0.07
     nas
    -0.07
     Sandra
    -0.06
     Ні
    -0.06
    ología
    -0.06
     Fred
    -0.06
    .xxx
    -0.06
    erno
    -0.06
    격
    -0.06
     parental
    -0.06
    POSITIVE LOGITS
    annon
    0.07
    ilogue
    0.07
    delay
    0.06
    ."
    0.06
     steals
    0.06
    /gr
    0.06
    _tensor
    0.06
    安全
    0.06
    -ब
    0.06
    ，在
    0.06
    Act Density 0.057%

    No Known Activations