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

    Neuronpedia

    INDEX
    Explanations

    legal/official processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stable
    -0.07
    	payload
    -0.07
    .variable
    -0.06
     squares
    -0.06
     DIG
    -0.06
    -0.06
    lop
    -0.06
    ीध
    -0.06
     Ir
    -0.06
     embedding
    -0.06
    POSITIVE LOGITS
     ButterKnife
    0.07
    AIL
    0.07
    (tol
    0.07
     Parsing
    0.07
     akci
    0.07
    (Result
    0.06
     breat
    0.06
    [hash
    0.06
     їм
    0.06
    .strategy
    0.06
    Act Density 0.030%

    No Known Activations