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

    Neuronpedia

    INDEX
    Explanations

    the preposition "in" across various contexts

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

    keep in mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.77
    verwijspagina
    -0.64
    UserScript
    -0.63
    -0.63
     дописавши
    -0.63
     CanadaChoose
    -0.62
     HasFactory
    -0.60
     Wikimedijinoj
    -0.60
     outlawed
    -0.54
    脚注の使い方
    -0.53
    POSITIVE LOGITS
     note
    0.46
     Note
    0.40
    buie
    0.38
     sure
    0.37
     faith
    0.36
     feel
    0.36
    秉
    0.36
     reference
    0.35
    Note
    0.34
     liên
    0.34
    Act Density 0.010%

    No Known Activations