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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and actions

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

    followed by "is," "has," or similar verbs

    np_acts-logits-general · gemini-2.0-flash

    state or outcome description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.72
    ()].
    -0.66
     чтоб
    -0.66
    mybatisplus
    -0.65
    脚注の使い方
    -0.65
    клопе
    -0.64
    RegressionTest
    -0.63
    ()];
    -0.63
     disambiguazione
    -0.62
    Personensuche
    -0.60
    POSITIVE LOGITS
     is
    2.19
     has
    1.82
     was
    1.49
     can
    1.41
     will
    1.40
     may
    1.31
     cannot
    1.29
     isn
    1.22
     seems
    1.20
     appears
    1.17
    Act Density 4.824%

    No Known Activations