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

    Neuronpedia

    INDEX
    Explanations

    Language context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clamp
    -0.09
     Ideally
    -0.08
    eble
    -0.08
     глад
    -0.08
     Archae
    -0.08
     clamp
    -0.08
     Batista
    -0.08
     Truly
    -0.08
     Accurate
    -0.07
    angano
    -0.07
    POSITIVE LOGITS
    Coffee
    0.08
    uut
    0.08
     description
    0.08
     pretty
    0.07
    nature
    0.07
    Salon
    0.07
     texting
    0.07
    mention
    0.07
    תח
    0.07
     উল্লেখ
    0.07
    Act Density 0.021%

    No Known Activations