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

    Neuronpedia

    INDEX
    Explanations

    expressions related to questioning or doubt about actions and statements

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

    Comes after punctuation

    np_acts-logits-general · gemini-2.0-flash

    punctuation and sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zero
    -0.51
    abstractmethod
    -0.50
     bodyParser
    -0.49
    enumii
    -0.49
     zeroes
    -0.48
    ंदीखरीदारी
    -0.47
    ssil
    -0.46
    Caratteristiche
    -0.46
    zule
    -0.45
    AlterField
    -0.44
    POSITIVE LOGITS
    localctx
    0.69
    確かに
    0.67
    たしか
    0.66
     truth
    0.63
    modb
    0.63
     Roskov
    0.61
     <=",
    0.61
     verdade
    0.58
    いえ
    0.57
     catholique
    0.57
    Act Density 0.297%

    No Known Activations