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

    Neuronpedia

    INDEX
    Explanations

    data types and schemas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دوا
    0.43
    റ്റി
    0.42
    WallArray
    0.39
    UIManager
    0.39
    LVector
    0.39
    Hill
    0.39
    addEdge
    0.38
    輝
    0.38
    董
    0.38
    THRESH
    0.37
    POSITIVE LOGITS
    minLength
    0.93
     maxLength
    0.81
    maxLength
    0.79
     pattern
    0.75
    MaxLength
    0.73
    pattern
    0.71
     Pattern
    0.71
    Pattern
    0.71
    length
    0.70
     required
    0.69
    Act Density 0.016%

    No Known Activations