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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and publications

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

    academic journal titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.47
    addCriterion
    -0.47
    RegressionTest
    -0.46
    AccessorTable
    -0.42
    GOTREF
    -0.41
    EndGlobalSection
    -0.40
     Taktlose
    -0.40
    IBAction
    -0.38
    -------
    -0.37
    Personendaten
    -0.37
    POSITIVE LOGITS
     queſto
    0.55
    ⏡
    0.53
    Composição
    0.52
    ſammen
    0.51
    cbx
    0.50
    EnglishChoose
    0.49
     voisins
    0.49
    Semoga
    0.49
     ويكيپ
    0.49
    elski
    0.48
    Act Density 0.445%

    No Known Activations