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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $n
    -0.07
     ben
    -0.06
     incentives
    -0.06
     Cain
    -0.06
    managedType
    -0.06
    QUEST
    -0.06
     Reyes
    -0.06
     ап
    -0.06
     HEX
    -0.06
    _pag
    -0.06
    POSITIVE LOGITS
    Cro
    0.07
    ()),↵
    0.07
    ICTURE
    0.07
    Following
    0.07
    ?>↵
    0.07
     사망
    0.07
     DERP
    0.07
     >↵
    0.07
    /><
    0.06
    ?>↵↵
    0.06
    Act Density 0.006%

    No Known Activations