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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Utility
    -0.07
    Normalization
    -0.07
    record
    -0.07
    CRY
    -0.07
    /ca
    -0.07
    .partition
    -0.06
    _report
    -0.06
    -formed
    -0.06
    Indexed
    -0.06
    .Toggle
    -0.06
    POSITIVE LOGITS
     облас
    0.06
     th�
    0.06
     Tata
    0.06
    мерикан
    0.06
    James
    0.06
     pobl
    0.05
     laut
    0.05
     ModelAndView
    0.05
     weapon
    0.05
    086
    0.05
    Act Density 0.002%

    No Known Activations