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

    Neuronpedia

    INDEX
    Explanations

    email address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    answer
    0.65
     rekl
    0.65
    0.65
    sweep
    0.61
    %
    0.61
    period
    0.60
    categories
    0.59
    restaurants
    0.59
    advertising
    0.59
    select
    0.59
    POSITIVE LOGITS
     얘가
    0.78
     −/−
    0.76
     Hfn
    0.75
    LPTMR
    0.75
     NLRP
    0.72
     fgets
    0.70
     upregulated
    0.68
     mAbs
    0.68
     upregulation
    0.66
     GSK
    0.66
    Act Density 0.036%

    No Known Activations