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

    Neuronpedia

    INDEX
    Explanations

    Conversational questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raq
    -0.07
    xfc
    -0.07
    _IRQ
    -0.07
    男
    -0.07
     Mai
    -0.07
    Full
    -0.07
    🍒
    -0.07
     exhaustive
    -0.07
    臀
    -0.07
    值得一
    -0.07
    POSITIVE LOGITS
    (icon
    0.07
    .ActionBar
    0.07
    Bạn
    0.07
     library
    0.07
    cannot
    0.07
    _operation
    0.07
    .header
    0.07
     Maintain
    0.07
    уют
    0.06
     bent
    0.06
    Act Density 0.045%

    No Known Activations