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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     latest
    -0.07
    Hands
    -0.06
     Analy
    -0.06
     بما
    -0.06
     lúc
    -0.06
    	mock
    -0.06
    Eval
    -0.06
    Bạn
    -0.06
    College
    -0.06
     Viktor
    -0.06
    POSITIVE LOGITS
    =%
    0.07
     seafood
    0.07
    _aux
    0.06
     blockers
    0.06
    jourd
    0.06
     Outputs
    0.06
    :::::::::::
    0.06
     林
    0.06
    Callbacks
    0.06
    [Int
    0.06
    Act Density 0.119%

    No Known Activations