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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ([]);↵↵
    -0.07
    CENTER
    -0.06
    .subscription
    -0.06
    composite
    -0.06
    '];
↵
↵
    -0.06
    并不
    -0.06
    관리자
    -0.06
     �
    -0.06
    vey
    -0.06
    .WEST
    -0.06
    POSITIVE LOGITS
     hes
    0.07
     wrestling
    0.07
    _tw
    0.06
    maximum
    0.06
    uctions
    0.06
     prevented
    0.06
    successful
    0.06
    .Enums
    0.06
     felt
    0.06
     kind
    0.06
    Act Density 0.038%

    No Known Activations