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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to equations or algorithms

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

    Mathematical expressions with exponents

    np_acts-logits-general · gemini-2.0-flash

    number 2 as exponent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused23>
    -0.81
    [@BOS@]
    -0.81
    <unused8>
    -0.81
    <unused16>
    -0.81
    <unused14>
    -0.81
    <unused74>
    -0.81
    <unused28>
    -0.81
    <unused43>
    -0.81
    <unused41>
    -0.80
    <unused42>
    -0.80
    POSITIVE LOGITS
     square
    0.35
     net
    0.33
    kháu
    0.30
     shot
    0.30
     di
    0.30
     dip
    0.29
     quadratic
    0.28
     de
    0.28
     ground
    0.28
    2
    0.27
    Act Density 1.716%

    No Known Activations