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

    Neuronpedia

    INDEX
    Explanations

    web development data science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rapping
    0.46
     transformer
    0.43
     motionProxy
    0.43
     gable
    0.42
     mycursor
    0.41
     purse
    0.41
     putea
    0.41
     sunny
    0.41
     insertion
    0.39
     multimillion
    0.39
    POSITIVE LOGITS
    Quantity
    0.55
    Value
    0.52
    ed
    0.50
    0
    0.49
    3
    0.46
    Children
    0.45
    Indicator
    0.45
    I
    0.45
    Z
    0.45
    value
    0.45
    Act Density 0.001%

    No Known Activations