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

    Neuronpedia

    INDEX
    Explanations

    research/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	↵	↵	↵
    -0.07
     Tumblr
    -0.07
     Ville
    -0.07
     Sketch
    -0.07
     intval
    -0.07
     bac
    -0.07
    (FALSE
    -0.06
     Wasser
    -0.06
    .Translate
    -0.06
    интер
    -0.06
    POSITIVE LOGITS
    Capability
    0.07
    тар
    0.07
    بحر
    0.07
    remain
    0.07
    특
    0.07
    連れ
    0.07
     seas
    0.07
     PRIV
    0.06
    >-
    0.06
    בע
    0.06
    Act Density 0.810%

    No Known Activations