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

    Neuronpedia

    INDEX
    Explanations

    players

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nge
    -0.07
     revolves
    -0.07
     strengthens
    -0.07
     kw
    -0.07
    _content
    -0.07
    COMMAND
    -0.07
    Ｂ
    -0.06
    Spider
    -0.06
    .Selected
    -0.06
     Olympic
    -0.06
    POSITIVE LOGITS
     reversible
    0.06
     afflict
    0.06
    (et
    0.06
     ['/
    0.06
    문제
    0.06
    �
    0.06
    ...↵↵
    0.06
    ...↵
    0.06
    Tôi
    0.06
    bios
    0.06
    Act Density 0.000%

    No Known Activations