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

    Neuronpedia

    INDEX
    Explanations

    technical concepts and terminology related to programming and linguistics

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

    keywords and particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.67
    CppMethod
    -0.58
    msgTypes
    -0.52
    참고
    -0.52
     asesinado
    -0.52
     kollu
    -0.50
     otomatig
    -0.50
    Спољашње
    -0.48
    uVar
    -0.47
    Personendaten
    -0.47
    POSITIVE LOGITS
     word
    0.43
     words
    0.38
     phrase
    0.37
     modifier
    0.37
     adverb
    0.37
     keyword
    0.37
     pronoun
    0.36
     MainAxisSize
    0.36
     modifiers
    0.36
    <bos>
    0.35
    Act Density 0.206%

    No Known Activations