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

    Neuronpedia

    INDEX
    Explanations

    code/formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     complains
    -0.08
    -slot
    -0.07
     abducted
    -0.06
    _radius
    -0.06
    CALL
    -0.06
     McConnell
    -0.06
     calendars
    -0.06
     AI
    -0.06
    昉
    -0.06
    $con
    -0.06
    POSITIVE LOGITS
    ダウン
    0.07
    听到
    0.07
    عالم
    0.07
    ided
    0.07
    atoms
    0.06
    輸
    0.06
    jak
    0.06
    ternal
    0.06
    充分利用
    0.06
    世界上
    0.06
    Act Density 0.078%

    No Known Activations