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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рад
    -0.07
    번
    -0.07
    MouseListener
    -0.07
    .vars
    -0.06
    息
    -0.06
    apt
    -0.06
    avern
    -0.06
    Το
    -0.06
    }/${
    -0.06
    ครง
    -0.06
    POSITIVE LOGITS
     adidas
    0.07
     만족
    0.06
     accordingly
    0.06
     �
    0.06
     Staff
    0.06
    _EDITOR
    0.06
     alcohol
    0.06
     ремон
    0.06
     والإ
    0.06
    ="(
    0.06
    Act Density 0.009%

    No Known Activations