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

    Neuronpedia

    INDEX
    Explanations

    erotic stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这里
    -0.08
    $criteria
    -0.07
     المر
    -0.07
     dirty
    -0.07
     어
    -0.06
     díky
    -0.06
    mtree
    -0.06
     CONSTRAINT
    -0.06
    르게
    -0.06
    EK
    -0.06
    POSITIVE LOGITS
    .:.:.:.:
    0.06
    AILY
    0.06
    Fit
    0.06
    .Down
    0.06
     recycled
    0.06
    Thor
    0.06
    ・・・
    0.06
     inj
    0.06
     trespass
    0.06
    âte
    0.05
    Act Density 0.019%

    No Known Activations