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

    Neuronpedia

    INDEX
    Explanations

    requests or commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声明
    -0.07
    _spell
    -0.06
    トル
    -0.06
    .hist
    -0.06
    技术
    -0.06
     pressing
    -0.06
    르는
    -0.06
     fetish
    -0.06
     rivalry
    -0.06
    isLoading
    -0.06
    POSITIVE LOGITS
    言
    0.07
     言
    0.06
    ghest
    0.06
     bootstrap
    0.06
    ，从
    0.06
     inherently
    0.06
    ercul
    0.06
     Duel
    0.06
    ーネ
    0.06
     zdję
    0.05
    Act Density 0.050%

    No Known Activations