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

    Neuronpedia

    INDEX
    Explanations

    romance/sexual content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fue
    -0.07
     kot
    -0.07
     tx
    -0.07
    _pins
    -0.06
    任务
    -0.06
     Philippine
    -0.06
    opez
    -0.06
     taky
    -0.06
    Evidence
    -0.06
    spa
    -0.06
    POSITIVE LOGITS
    wik
    0.07
    '(
    0.06
    ादन
    0.06
     civilized
    0.06
     похож
    0.06
    置
    0.06
    mpr
    0.06
    |$
    0.06
    услов
    0.06
    ocate
    0.06
    Act Density 0.056%

    No Known Activations