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

    Neuronpedia

    INDEX
    Explanations

    references to time intervals and the concept of progression

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

    so far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.65
     snippetHide
    -0.56
    })->
    -0.53
    -0.53
    majánló
    -0.52
     enfans
    -0.52
     aislado
    -0.51
     étoient
    -0.51
     avoient
    -0.51
     prohibido
    -0.50
    POSITIVE LOGITS
    .
    0.55
    omitempty
    0.53
    ,
    0.51
    …
    0.44
    anyway
    0.44
     حاضر
    0.44
    imanapun
    0.43
     зараз
    0.43
    ViewFeatures
    0.42
    InBackground
    0.42
    Act Density 0.047%

    No Known Activations