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

    Neuronpedia

    INDEX
    Explanations

    question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GMC
    -0.06
     다
    -0.06
    تری
    -0.06
    BuilderFactory
    -0.06
     Har
    -0.06
    niej
    -0.06
     ─
    -0.06
    	T
    -0.06
     TERM
    -0.06
    θή
    -0.06
    POSITIVE LOGITS
     lạnh
    0.08
     QT
    0.08
     comply
    0.07
     consolation
    0.07
     Inspector
    0.07
     fora
    0.06
     fantastic
    0.06
     continuation
    0.06
    arse
    0.06
     Mädchen
    0.06
    Act Density 0.028%

    No Known Activations