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

    Neuronpedia

    INDEX
    Explanations

    senior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    foreach
    -0.07
     vừa
    -0.06
    	spec
    -0.06
     run
    -0.06
    高
    -0.06
    Against
    -0.06
    Aut
    -0.06
    ,o
    -0.06
     كن
    -0.06
     qw
    -0.06
    POSITIVE LOGITS
    illusion
    0.06
    lasyon
    0.06
     significa
    0.06
    roma
    0.06
    orelease
    0.06
    xmlns
    0.06
    Ο�
    0.06
    ETA
    0.06
     structured
    0.06
     accordance
    0.06
    Act Density 0.039%

    No Known Activations