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

    Neuronpedia

    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fuel
    -0.08
     keuntungan
    -0.08
    iosamente
    -0.08
    ความคิดเห็น
    -0.08
     انرژی
    -0.07
    Energy
    -0.07
    تی
    -0.07
    Binary
    -0.07
    änk
    -0.07
     discurs
    -0.07
    POSITIVE LOGITS
     beginners
    0.10
     DIY
    0.09
     novices
    0.09
    初心
    0.09
     novice
    0.09
     beginner
    0.09
     guidance
    0.08
    指导
    0.08
     idiot
    0.08
    指南
    0.08
    Act Density 0.021%

    No Known Activations