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

    Neuronpedia

    INDEX
    Explanations

    impressive

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Infinite
    0.60
     Infinite
    0.51
     finalidad
    0.50
    Unlimited
    0.50
     Theoretically
    0.49
     প্রচলিত
    0.49
     infinitely
    0.49
    initely
    0.48
     infinite
    0.47
     inherently
    0.47
    POSITIVE LOGITS
     impressive
    1.92
    impress
    1.40
     spectacular
    1.36
     impressively
    1.31
     beeindruck
    1.30
    Impress
    1.25
     record
    1.23
     remarkable
    1.23
     stunning
    1.23
     impressing
    1.22
    Act Density 0.137%

    No Known Activations