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

    Neuronpedia

    INDEX
    Explanations

    publication information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bactéries
    0.72
    nel
    0.71
     alguns
    0.70
    IAT
    0.69
    né
    0.68
    Many
    0.68
    IN
    0.66
    Let
    0.66
     algumas
    0.66
    În
    0.65
    POSITIVE LOGITS
     publication
    0.59
     work
    0.59
     public
    0.58
     burial
    0.58
     crime
    0.57
     publish
    0.56
     north
    0.56
     rainbow
    0.56
     ribbon
    0.56
     vested
    0.56
    Act Density 0.012%

    No Known Activations