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

    Neuronpedia

    INDEX
    Explanations

    refer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    心理
    -0.06
    straint
    -0.06
     laid
    -0.06
    gram
    -0.06
    cold
    -0.06
    [color
    -0.06
     veil
    -0.06
    CanBe
    -0.06
    nesota
    -0.06
     underscore
    -0.05
    POSITIVE LOGITS
    .selenium
    0.07
     Computes
    0.07
    .StylePriority
    0.07
    .Usuario
    0.06
     opc
    0.06
     dataSet
    0.06
     تق
    0.06
    Searching
    0.06
    .choices
    0.06
    .false
    0.06
    Act Density 0.025%

    No Known Activations