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

    Neuronpedia

    INDEX
    Explanations

    discussions about exceptions and specific details in contexts involving agreements or references

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

    Language indicating infrequency or small quantity

    np_acts-logits-general · gemini-2.0-flash

    only a few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.51
    }{*}{}
    -0.50
     all
    -0.47
    UnusedPrivate
    -0.46
    feinander
    -0.46
    rmızı
    -0.46
    又是
    -0.45
    Simult
    -0.44
    клад
    -0.44
    assertEqual
    -0.44
    POSITIVE LOGITS
     briefly
    1.81
     occasional
    1.72
     occasionally
    1.66
     slightly
    1.62
     quelques
    1.58
     slight
    1.53
     mildly
    1.50
    slightly
    1.47
     Occasionally
    1.47
     sedikit
    1.46
    Act Density 0.973%

    No Known Activations