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

    Neuronpedia

    INDEX
    Explanations

    code syntax/comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cho
    -0.07
    527
    -0.06
     most
    -0.06
    UFFIX
    -0.06
     děl
    -0.06
     Collins
    -0.06
     Min
    -0.06
     Max
    -0.06
     Fortune
    -0.06
    lamp
    -0.06
    POSITIVE LOGITS
    ITLE
    0.07
     brokers
    0.06
     advis
    0.06
    ,map
    0.06
    ";}
    0.06
     passages
    0.06
    embros
    0.06
    .cloudflare
    0.06
    ;}
    0.06
     olay
    0.06
    Act Density 0.027%

    No Known Activations