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

    Neuronpedia

    INDEX
    Explanations

    Standardized tests excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    环球
    -0.07
     Raspberry
    -0.06
    ﯖ
    -0.06
     cheque
    -0.06
     Be
    -0.06
     bcrypt
    -0.06
    的前提下
    -0.06
     Competition
    -0.06
    olation
    -0.06
    会
    -0.06
    POSITIVE LOGITS
    format
    0.08
     unseren
    0.07
    [System
    0.07
    ออกจาก
    0.07
     мой
    0.07
    _mem
    0.07
     elder
    0.07
    VICES
    0.07
    ASCII
    0.06
     henne
    0.06
    Act Density 0.030%

    No Known Activations