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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    就是因为
    -0.07
    Не
    -0.07
    ].[
    -0.07
    Female
    -0.07
     После
    -0.07
     summoned
    -0.06
    踹
    -0.06
     temp
    -0.06
    ない
    -0.06
    生猪
    -0.06
    POSITIVE LOGITS
    בי
    0.07
    ™
    0.07
    بان
    0.07
     SITE
    0.07
    -br
    0.07
    ⚘
    0.07
    Prototype
    0.07
    更快
    0.07
    input
    0.07
    芳香
    0.07
    Act Density 0.083%

    No Known Activations