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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     მომხმარ
    -0.08
     ગ્રાહ
    -0.08
     segmentation
    -0.08
    utang
    -0.08
    hta
    -0.08
     없이
    -0.08
    usid
    -0.08
     humanities
    -0.08
     commission
    -0.08
     امکان
    -0.08
    POSITIVE LOGITS
     Publications
    0.08
    निक
    0.07
    ZONE
    0.07
     extracts
    0.07
     misleading
    0.07
     Groups
    0.07
     extracted
    0.07
     Publ
    0.07
    -utils
    0.07
     dieser
    0.07
    Act Density 0.001%

    No Known Activations