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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conditions and restrictions in discourse

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

    Follows quotation marks

    np_acts-logits-general · gemini-2.0-flash

    defining specific terms in quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.61
    bleshooting
    -0.50
    openqa
    -0.50
     مواليد
    -0.49
    ures
    -0.47
    Xna
    -0.46
     fi
    -0.46
     كورة
    -0.46
    Recu
    -0.46
    เต
    -0.45
    POSITIVE LOGITS
    ///</
    0.74
     ddelweddau
    0.71
    脚注の使い方
    0.68
    bootstrapcdn
    0.68
    =“
    0.67
     sacré
    0.66
    లాలు
    0.64
    Jegyzetek
    0.64
     trattano
    0.63
     plural
    0.60
    Act Density 0.467%

    No Known Activations