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

    Neuronpedia

    INDEX
    Explanations

    Code/file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yellow
    -0.09
     sunset
    -0.08
     Manson
    -0.08
     vehicles
    -0.08
    hurst
    -0.07
     answers
    -0.07
    export
    -0.07
    351
    -0.07
    หย
    -0.07
     Treatment
    -0.07
    POSITIVE LOGITS
     tín
    0.06
    着
    0.06
    따
    0.06
    itä
    0.06
     화
    0.06
    σχ
    0.06
    іли
    0.06
    ляет
    0.06
    /forms
    0.06
    奴
    0.06
    Act Density 0.006%

    No Known Activations