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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to scientific studies and discussions

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

    before commas

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    让她
    -0.63
    让他
    -0.57
    herself
    -0.53
    mybatisplus
    -0.53
    和他
    -0.53
     lui
    -0.52
    是她
    -0.52
    在他的
    -0.51
    porque
    -0.51
    把他
    -0.51
    POSITIVE LOGITS
     there
    1.73
     they
    1.71
     we
    1.70
     it
    1.48
     you
    1.31
    there
    1.13
     he
    1.11
     nobody
    1.05
     nothing
    1.03
     the
    1.03
    Act Density 1.366%

    No Known Activations