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

    Neuronpedia

    INDEX
    Explanations

    Murder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Forget
    -0.07
    bullet
    -0.06
     Diy
    -0.06
    _join
    -0.06
     Imports
    -0.06
    highlight
    -0.06
     аллерг
    -0.06
    PX
    -0.06
    DETAIL
    -0.06
    );*/↵
    -0.06
    POSITIVE LOGITS
    eci
    0.08
     etti
    0.07
    046
    0.07
     fitness
    0.07
     (![
    0.07
    -ne
    0.06
    446
    0.06
     kim
    0.06
    ****↵
    0.06
    <|end_header_id|>
    0.06
    Act Density 0.045%

    No Known Activations