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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding legal rights and privileges

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

    followed by negations or qualifications

    np_acts-logits-general · gemini-2.0-flash

    is a or is not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.65
    RegressionTest
    -0.65
    ThroughAttribute
    -0.64
     affectionately
    -0.63
     otomatig
    -0.63
    protoimpl
    -0.63
    tagHelper
    -0.60
    unnitel
    -0.59
    -0.59
    améli
    -0.58
    POSITIVE LOGITS
     presup
    0.62
     implied
    0.56
     tauto
    0.54
     vazio
    0.54
     entail
    0.53
    evsky
    0.53
     presupposes
    0.53
     constitutive
    0.52
     impli
    0.50
     entailed
    0.50
    Act Density 0.678%

    No Known Activations