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

    Neuronpedia

    INDEX
    Explanations

    ive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /math
    -0.09
     calculus
    -0.07
    coin
    -0.07
     coin
    -0.07
    .full
    -0.07
    理解
    -0.07
     panc
    -0.07
     Stein
    -0.07
    する
    -0.07
    𝐓
    -0.07
    POSITIVE LOGITS
    emons
    0.07
    .LOC
    0.07
     vibes
    0.07
     Jobs
    0.07
    حصل
    0.07
    .Alert
    0.06
    ⏲
    0.06
     Celebr
    0.06
     объя
    0.06
    大量
    0.06
    Act Density 0.002%

    No Known Activations