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

    Neuronpedia

    INDEX
    Explanations

    treatment resistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depois
    -0.08
    .question
    -0.07
    .executor
    -0.07
    徒弟
    -0.07
    InterfaceOrientation
    -0.07
    -peer
    -0.07
     *))
    -0.07
    ESSAGE
    -0.06
    车子
    -0.06
     unfolding
    -0.06
    POSITIVE LOGITS
    кри
    0.07
    Cell
    0.07
     ******************************************************************************/↵↵
    0.06
     Fare
    0.06
     Gate
    0.06
    黑夜
    0.06
    _Variable
    0.06
    中心城市
    0.06
     crises
    0.06
     Holly
    0.06
    Act Density 0.020%

    No Known Activations