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

    Neuronpedia

    INDEX
    Explanations

    guarantee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parts
    -0.07
     works
    -0.07
    olders
    -0.07
    년에
    -0.06
     began
    -0.06
    sed
    -0.06
     black
    -0.06
     limb
    -0.06
     bilder
    -0.06
     多
    -0.06
    POSITIVE LOGITS
     guarantee
    0.11
     guarantees
    0.08
     GHz
    0.08
     Assurance
    0.07
     garant
    0.07
     Gam
    0.07
     Guarantee
    0.07
    ataka
    0.07
     guaranteed
    0.07
     hatır
    0.06
    Act Density 0.021%

    No Known Activations