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

    Neuronpedia

    INDEX
    Explanations

    proper nouns associated with notable individuals and their relationships

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

    First name followed by last name initial

    np_acts-logits-general · gemini-2.0-flash

    names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.45
     i
    -0.43
     U
    -0.42
     F
    -0.41
     C
    -0.41
    โล
    -0.41
     c
    -0.40
    <bos>
    -0.40
     D
    -0.40
     hasattr
    -0.40
    POSITIVE LOGITS
     myſelf
    0.88
     itſelf
    0.87
    SourceChecksum
    0.85
     Monfieur
    0.84
     Chriftian
    0.84
     Jefus
    0.84
     Theſe
    0.81
     doubtnut
    0.79
     ſeveral
    0.78
     Houſe
    0.77
    Act Density 0.122%

    No Known Activations