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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assumed
    -0.06
     Himal
    -0.06
     waitFor
    -0.06
    国资
    -0.06
    autoload
    -0.06
     пласт
    -0.06
    园林
    -0.06
     finder
    -0.06
     plaintiffs
    -0.06
    (?
    -0.06
    POSITIVE LOGITS
    -view
    0.07
    .Println
    0.07
    jąc
    0.07
     masc
    0.07
    .VK
    0.07
    so
    0.06
     mdi
    0.06
    shiv
    0.06
    轮流
    0.06
    vant
    0.06
    Act Density 0.142%

    No Known Activations