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

    Neuronpedia

    INDEX
    Explanations

    Questions and prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bus
    -0.07
    Awesome
    -0.07
    ourney
    -0.07
    ãy
    -0.06
    ffiti
    -0.06
     additive
    -0.06
    ابقات
    -0.06
     Cs
    -0.06
    攻击
    -0.06
    .Margin
    -0.06
    POSITIVE LOGITS
    _Version
    0.07
     TEAM
    0.06
    зд
    0.06
    types
    0.06
    بس
    0.06
    ,port
    0.06
    conomics
    0.06
    brıs
    0.06
    override
    0.06
    एन
    0.06
    Act Density 0.025%

    No Known Activations