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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dates and numbers with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.68
     للمعارف
    -0.68
    ðsíða
    -0.66
    citroën
    -0.63
     menschlichen
    -0.63
     colgantes
    -0.63
     colgante
    -0.63
    elashes
    -0.63
     ſich
    -0.63
    Spolja
    -0.62
    POSITIVE LOGITS
    0
    0.81
     Zero
    0.49
    Zero
    0.49
     zero
    0.41
     jPanel
    0.39
    zero
    0.38
    No
    0.35
    ０
    0.35
    übung
    0.34
     ZERO
    0.34
    Act Density 0.005%

    No Known Activations