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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Constitutional
    -0.07
     所
    -0.07
     handguns
    -0.07
    (which
    -0.07
    pective
    -0.06
     Mexican
    -0.06
     世界
    -0.06
    ertura
    -0.06
     Unknown
    -0.06
    atic
    -0.06
    POSITIVE LOGITS
    ंय
    0.07
    响
    0.06
     helicopt
    0.06
    [K
    0.06
    LOPT
    0.06
    Paper
    0.06
     vinyl
    0.06
    �
    0.06
     syll
    0.06
    ‐'
    0.06
    Act Density 0.028%

    No Known Activations