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

    Neuronpedia

    INDEX
    Explanations

    coarse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    horabuena
    -1.13
     fine
    -1.05
    queryInterface
    -1.05
    berdayakan
    -0.96
     Paglinawan
    -0.95
    Fine
    -0.94
    rungsseite
    -0.93
     snippetHide
    -0.93
    ergies
    -0.93
     Lightboxes
    -0.92
    POSITIVE LOGITS
     CO
    0.64
    CO
    0.63
    ,
    0.63
     C
    0.61
     
    0.57
    co
    0.57
    Co
    0.57
    top
    0.56
     (
    0.55
     person
    0.55
    Act Density 0.061%

    No Known Activations