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

    Neuronpedia

    INDEX
    Explanations

    occurrences of HTML and JavaScript tags

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

    HTML attributes and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.91
     queſta
    -0.91
    tvguidetime
    -0.82
     zwiſchen
    -0.77
     ſei
    -0.73
     témoig
    -0.73
    SharedDtor
    -0.73
    RegressionTest
    -0.72
    transQ
    -0.71
     ſoll
    -0.71
    POSITIVE LOGITS
     or
    0.40
     see
    0.39
     either
    0.35
     also
    0.35
     not
    0.34
     =
    0.31
    ăți
    0.31
     be
    0.30
     to
    0.29
     ,
    0.29
    Act Density 0.011%

    No Known Activations