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

    Neuronpedia

    INDEX
    Explanations

    acknowledgement phrases and references to external sources

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

    Non-English text, labels, and uncommon words

    np_acts-logits-general · gemini-2.0-flash

    Danish movie titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    namt
    -0.48
     GetEnumerator
    -0.44
    RotationOrder
    -0.43
     orders
    -0.39
    cross
    -0.39
    亨
    -0.38
    FlowLayout
    -0.37
    StringBuilder
    -0.37
     Utopia
    -0.37
    SetBool
    -0.37
    POSITIVE LOGITS
    illige
    0.65
    ErrUnexpectedEOF
    0.64
     Guille
    0.63
    expandindo
    0.62
     связанные
    0.62
     protoimpl
    0.61
    ervative
    0.61
    marle
    0.60
    Newswire
    0.59
     препратки
    0.59
    Act Density 0.037%

    No Known Activations