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

    Neuronpedia

    INDEX
    Explanations

    onboarding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alcan
    -0.08
     adulter
    -0.08
     alcançar
    -0.07
     atingir
    -0.07
    �
    -0.07
     Venus
    -0.07
     dab
    -0.07
    vg
    -0.07
     Verkehr
    -0.07
    ationship
    -0.07
    POSITIVE LOGITS
     onboarding
    0.10
     സ്വാഗത
    0.10
    启动
    0.09
     स्वागत
    0.09
    手续
    0.09
     लॉन्च
    0.09
    流程
    0.09
     কর্ম
    0.08
    Startup
    0.08
    Welcome
    0.08
    Act Density 0.015%

    No Known Activations