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

    Neuronpedia

    INDEX
    Explanations

    explaining technical or formal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LVector
    0.53
     importante
    0.50
     सीटेट
    0.47
    ？](
    0.47
    kommun
    0.46
    DueDate
    0.46
    MESSAGE
    0.46
    GUARD
    0.46
    Rover
    0.45
    㻐
    0.45
    POSITIVE LOGITS
    0
    0.56
     B
    0.53
     E
    0.50
     to
    0.49
     counties
    0.47
     Y
    0.46
     draws
    0.45
     pint
    0.45
     M
    0.44
     tob
    0.44
    Act Density 0.015%

    No Known Activations