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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _GL
    -0.07
    thren
    -0.07
     paras
    -0.07
    RICT
    -0.07
     implications
    -0.06
     drivers
    -0.06
     FOX
    -0.06
     validated
    -0.06
     bet
    -0.06
    ],[
    -0.06
    POSITIVE LOGITS
    kea
    0.07
    >Main
    0.06
    inspect
    0.06
     Secondary
    0.06
    xmin
    0.06
    دهای
    0.06
     줄
    0.06
    保
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.06
    惊
    0.06
    Act Density 0.010%

    No Known Activations