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

    Neuronpedia

    INDEX
    Explanations

    sentences that convey conclusions or final remarks

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

    Quoted speech or direct quotes

    np_acts-logits-general · gemini-2.0-flash

    attribution and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.87
    IntoConstraints
    -0.68
    bootstrapcdn
    -0.66
     CreateTagHelper
    -0.65
    twimg
    -0.63
     («
    -0.58
     nahilalakip
    -0.57
    SourceChecksum
    -0.56
    LookAnd
    -0.55
     (“
    -0.55
    POSITIVE LOGITS
     adding
    0.69
     referring
    0.59
     added
    0.59
     Adds
    0.59
    adding
    0.58
    etragen
    0.58
     aggiunto
    0.58
    __).
    0.58
    NUMX
    0.56
    Adding
    0.56
    Act Density 0.030%

    No Known Activations