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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a variety or multitude of subjects and details

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

    other plus nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.62
    EndContext
    -0.61
    windowFixed
    -0.58
    tanleria
    -0.56
    uxxxx
    -0.52
     kasarigan
    -0.51
    setVerticalGroup
    -0.50
     Савезне
    -0.50
    fromnode
    -0.50
     cherchés
    -0.50
    POSITIVE LOGITS
     stuff
    0.47
    AndEndTag
    0.43
     things
    0.41
    的一些
    0.40
     abbildung
    0.37
     cosas
    0.36
     eenige
    0.36
     række
    0.36
     segala
    0.36
    didSet
    0.36
    Act Density 0.043%

    No Known Activations