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

    Neuronpedia

    INDEX
    Explanations

    IS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toward
    -0.07
    entialAction
    -0.07
     towards
    -0.07
    GO
    -0.07
    Capt
    -0.06
     arrogant
    -0.06
    InlineData
    -0.06
     embarked
    -0.06
    SCI
    -0.06
    Them
    -0.06
    POSITIVE LOGITS
    _chunks
    0.07
    ++,
    0.07
    .Categories
    0.06
     datové
    0.06
     Yii
    0.06
    Framework
    0.06
    aylor
    0.06
    때
    0.06
     USB
    0.06
     Českosloven
    0.06
    Act Density 0.000%

    No Known Activations