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

    Neuronpedia

    INDEX
    Explanations

    existing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realities
    -0.07
    ASH
    -0.06
     ста
    -0.06
     UT
    -0.06
    Quiet
    -0.06
     radically
    -0.06
    criptions
    -0.06
    _ob
    -0.06
    _COUNTER
    -0.06
     devote
    -0.06
    POSITIVE LOGITS
     withstand
    0.07
    (map
    0.06
    ()}>↵
    0.06
    )>↵
    0.06
     Spam
    0.06
    :A
    0.06
     $("<
    0.06
    -->↵
    0.06
    )}>↵
    0.06
    "};
↵
    0.06
    Act Density 0.018%

    No Known Activations