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

    Neuronpedia

    INDEX
    Explanations

    uh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Saint
    -0.09
    /--
    -0.08
     Slack
    -0.07
    ">
↵
↵
    -0.07
    -for
    -0.07
    Segoe
    -0.07
     [])↵↵
    -0.07
    👙
    -0.07
     Saint
    -0.07
    Index
    -0.07
    POSITIVE LOGITS
    がかか
    0.07
     bus
    0.07
     skeptic
    0.07
    �
    0.07
    :F
    0.07
    -expression
    0.07
    𝘱
    0.07
    =query
    0.07
     término
    0.07
     pervasive
    0.07
    Act Density 0.003%

    No Known Activations