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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prefab
    -0.07
    ebe
    -0.07
     KH
    -0.07
     busiest
    -0.07
    (factory
    -0.06
     currents
    -0.06
     Plymouth
    -0.06
    $item
    -0.06
     posing
    -0.06
    _plain
    -0.06
    POSITIVE LOGITS
    ほ
    0.06
     Insight
    0.06
    Foundation
    0.06
     så
    0.06
    탄
    0.06
    گو
    0.06
    IDE
    0.06
    haust
    0.06
     bitterly
    0.06
    كم
    0.06
    Act Density 0.019%

    No Known Activations