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

    Neuronpedia

    INDEX
    Explanations

    Election/release information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    떪
    -0.07
     Hung
    -0.07
    iet
    -0.07
    -public
    -0.07
    attention
    -0.07
    젔
    -0.07
     thắ
    -0.06
     anlaşıl
    -0.06
    interpreter
    -0.06
    .adapter
    -0.06
    POSITIVE LOGITS
     thousand
    0.07
    КО
    0.07
    .rank
    0.07
     모든
    0.07
     DAYS
    0.06
     Со
    0.06
    自愿
    0.06
     rejoice
    0.06
     FALL
    0.06
    VEN
    0.06
    Act Density 0.027%

    No Known Activations