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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and character names

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

    Appears before a name or initial

    np_acts-logits-general · gemini-2.0-flash

    common first names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ın
    -0.49
    a
    -0.48
    on
    -0.48
    an
    -0.48
     (
    -0.47
    um
    -0.46
     
    -0.44
    sob
    -0.44
    m
    -0.43
    en
    -0.43
    POSITIVE LOGITS
     Monfieur
    1.16
     Efq
    1.14
     Jefus
    1.11
     Theſe
    1.07
     Shakspeare
    1.06
     raiſ
    1.05
     uſed
    1.05
     Houſe
    1.04
     houſe
    1.01
     himſelf
    1.01
    Act Density 0.166%

    No Known Activations