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

    Neuronpedia

    INDEX
    Explanations

    polymers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helper
    -0.08
    %E
    -0.07
    较大
    -0.07
    精细化
    -0.07
    ędzi
    -0.07
    emat
    -0.07
     utils
    -0.07
    是如何
    -0.06
    𝙬
    -0.06
    损害
    -0.06
    POSITIVE LOGITS
    VPN
    0.07
    钦
    0.07
    TEMP
    0.07
    .controllers
    0.07
    ONE
    0.06
    Delay
    0.06
     Moo
    0.06
     HIS
    0.06
     Harden
    0.06
    TOTAL
    0.06
    Act Density 0.002%

    No Known Activations