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

    Neuronpedia

    INDEX
    Explanations

    erotic content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。\
    -0.07
    ']=="
    -0.07
    ้ไข
    -0.07
    058
    -0.06
    .CSS
    -0.06
     Olsen
    -0.06
    'є
    -0.06
    φαρ
    -0.06
    เคร
    -0.06
     poised
    -0.06
    POSITIVE LOGITS
    (Source
    0.07
     doorway
    0.07
    one
    0.06
    cliffe
    0.06
     Moon
    0.06
     campaigned
    0.06
     descending
    0.06
    (source
    0.06
    -born
    0.06
    っても
    0.06
    Act Density 0.006%

    No Known Activations