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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

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

    obs cot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étranger
    -0.43
     chrétien
    -0.41
    gründ
    -0.40
    featureID
    -0.40
     mâle
    -0.39
     congreso
    -0.39
     gelukkig
    -0.38
     león
    -0.37
     tuot
    -0.37
     volcán
    -0.36
    POSITIVE LOGITS
    
    0.57
    enumii
    0.49
    脚注の使い方
    0.49
     Bonne
    0.49
    ftagPool
    0.48
    ErrUnexpectedEOF
    0.48
    enumi
    0.47
     ComVisible
    0.47
    InSection
    0.46
     squir
    0.46
    Act Density 0.031%

    No Known Activations