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

    Neuronpedia

    INDEX
    Explanations

    code formatting and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    if
    0.96
    f
    0.93
    ė
    0.92
    ↵
    0.86
    е
    0.86
    b
    0.86
    eseorang
    0.78
    с
    0.78
    in
    0.77
    func
    0.77
    POSITIVE LOGITS
     fearing
    0.95
     subjecting
    0.89
    lara
    0.88
     굉장
    0.87
     և
    0.86
     gastritis
    0.85
    യുടെ
    0.84
     unpublished
    0.84
     classifying
    0.84
     genus
    0.83
    Act Density 0.222%

    No Known Activations