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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apo
    -0.08
     ọbụ
    -0.08
    Eligible
    -0.08
     mane
    -0.08
    起来
    -0.08
     الا
    -0.08
    ிலும்
    -0.07
     memenuhi
    -0.07
     رابطه
    -0.07
    elateerde
    -0.07
    POSITIVE LOGITS
     assumptions
    0.08
     laws
    0.08
     rules
    0.08
     NCC
    0.08
     paper
    0.08
     privacy
    0.08
     guidelines
    0.08
     regulations
    0.07
     नियम
    0.07
     कानून
    0.07
    Act Density 0.025%

    No Known Activations