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

    Neuronpedia

    INDEX
    Explanations

    Separating lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Melania
    -0.07
     Elon
    -0.07
     MediaTek
    -0.07
    精细化
    -0.07
    ￂ
    -0.07
     curriculum
    -0.07
     freelance
    -0.07
     Tk
    -0.07
    -0.06
    博士
    -0.06
    POSITIVE LOGITS
    'é
    0.07
    ABLE
    0.07
    uales
    0.07
    擊
    0.07
    withstanding
    0.07
     across
    0.07
    -print
    0.07
    داد
    0.07
    idad
    0.07
    错过
    0.07
    Act Density 0.004%

    No Known Activations