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

    Neuronpedia

    INDEX
    Explanations

    Mode

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Circle
    -0.07
    _echo
    -0.07
    _win
    -0.06
     perspectives
    -0.06
     Tweets
    -0.06
    tester
    -0.06
    pls
    -0.06
    -direct
    -0.06
     Income
    -0.06
    irs
    -0.06
    POSITIVE LOGITS
    fetchAll
    0.07
     중국
    0.07
    ALCHEMY
    0.07
    民族
    0.06
    碼
    0.06
     abusing
    0.06
     ketogenic
    0.06
     cycling
    0.06
    ськ
    0.06
     اش
    0.06
    Act Density 0.008%

    No Known Activations