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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and representations in scientific contexts

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

    corresponds to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Digite
    -0.28
    Resource
    -0.25
     …
    -0.25
     kiệm
    -0.25
     mieli
    -0.24
     and
    -0.23
     comenzado
    -0.23
     Gehirn
    -0.23
    RelativeTo
    -0.22
    Net
    -0.21
    POSITIVE LOGITS
     ſeines
    0.73
     dieſer
    0.73
     ſeinem
    0.71
    𑄣
    0.71
    <unused23>
    0.71
    <unused16>
    0.71
    <unused14>
    0.70
    <unused17>
    0.70
    <unused3>
    0.70
    [@BOS@]
    0.70
    Act Density 0.149%

    No Known Activations