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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dévelop
    -0.07
    >).
    -0.07
    (Card
    -0.06
     lick
    -0.06
    값
    -0.06
    008
    -0.06
     Stretch
    -0.06
    Uploader
    -0.06
    -0.06
     oxid
    -0.06
    POSITIVE LOGITS
     mes
    0.07
    _PIPELINE
    0.06
     presum
    0.06
     merchandise
    0.06
    :hidden
    0.06
     principle
    0.06
    (",");↵
    0.06
    wahl
    0.06
    textInput
    0.06
     moderator
    0.06
    Act Density 0.027%

    No Known Activations