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

    Neuronpedia

    INDEX
    Explanations

    occurrences of special characters and formatting codes

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

    Abbreviations followed by numbers or letters

    np_acts-logits-general · gemini-2.0-flash

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etheless
    -0.82
    +:+
    -0.72
    Incluso
    -0.68
     panoramique
    -0.63
     الرغم
    -0.63
    Overall
    -0.62
    vailable
    -0.62
    存于互联网档案馆
    -0.59
    mmate
    -0.58
    overall
    -0.58
    POSITIVE LOGITS
     Messrs
    0.53
    theilung
    0.51
    .—
    0.50
    wärts
    0.48
     aforesaid
    0.48
    InputTagHelper
    0.47
     ultimo
    0.46
     ditto
    0.45
     diterima
    0.45
     lato
    0.45
    Act Density 0.345%

    No Known Activations