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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    berapa
    -0.07
    invoke
    -0.06
    ora
    -0.06
    itez
    -0.06
    /IP
    -0.06
    Site
    -0.06
     �
    -0.06
    _complex
    -0.06
     roofing
    -0.06
    ницы
    -0.06
    POSITIVE LOGITS
     direction
    0.11
    direction
    0.09
     directions
    0.09
     Insights
    0.08
     manuscripts
    0.08
     embarked
    0.07
    发展
    0.07
     slate
    0.07
    行動
    0.07
     dismiss
    0.07
    Act Density 0.025%

    No Known Activations