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

    Neuronpedia

    INDEX
    Explanations

    erotica

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protocols
    -0.06
    Cars
    -0.06
    πως
    -0.06
    sec
    -0.06
     xin
    -0.06
    lettes
    -0.06
    professional
    -0.06
    per
    -0.06
    ofs
    -0.06
    ění
    -0.06
    POSITIVE LOGITS
    !!}
    0.07
     �
    0.07
    ?>>
    0.07
     SUPER
    0.07
     vad
    0.07
    enal
    0.07
     bảo
    0.06
    !)
    0.06
     ToString
    0.06
     �
    0.06
    Act Density 0.037%

    No Known Activations