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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pau
    -0.07
     violet
    -0.06
    ASIC
    -0.06
     lineage
    -0.06
     circles
    -0.06
     Beau
    -0.06
     defiant
    -0.06
     initialValue
    -0.06
    ladu
    -0.06
    atas
    -0.06
    POSITIVE LOGITS
    Happy
    0.07
    Site
    0.07
     perd
    0.06
    Installing
    0.06
     userInput
    0.06
     extremely
    0.06
    blk
    0.06
    ({})↵
    0.06
    Brush
    0.06
    .advance
    0.06
    Act Density 0.006%

    No Known Activations