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

    Neuronpedia

    INDEX
    Explanations

    CO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,test
    -0.07
    dělen
    -0.06
    .elapsed
    -0.06
    ize
    -0.06
     tallest
    -0.06
     crimson
    -0.06
    ssql
    -0.06
    JSGlobal
    -0.06
    一般
    -0.06
     pink
    -0.06
    POSITIVE LOGITS
    /o
    0.08
    BOR
    0.07
     WTO
    0.07
     Votes
    0.07
     Decomp
    0.07
     QS
    0.07
    LOS
    0.07
    弟
    0.07
     conquest
    0.07
    dbl
    0.07
    Act Density 0.060%

    No Known Activations