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

    Neuronpedia

    INDEX
    Explanations

    technical terms and notations related to mathematical models and fluid dynamics

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

    indexed mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.21
    ſſung
    -1.16
    <unused41>
    -1.14
    ðsíða
    -1.14
    <unused28>
    -1.14
    <unused8>
    -1.14
    <unused16>
    -1.13
    <unused17>
    -1.13
    <unused14>
    -1.13
    [@BOS@]
    -1.13
    POSITIVE LOGITS
     etc
    0.27
     
    0.24
     et
    0.23
     colspan
    0.22
     h
    0.22
    T
    0.22
     or
    0.20
     of
    0.20
    /
    0.20
     I
    0.19
    Act Density 0.078%

    No Known Activations