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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and structures within a formal context

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    relevant time frame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    -0.91
     ",
    -0.90
     de
    -0.88
     -
    -0.88
     ๆ
    -0.87
     I
    -0.84
     )
    -0.83
     van
    -0.83
     y
    -0.83
    *",
    -0.82
    POSITIVE LOGITS
     itſelf
    1.61
     pleaſure
    1.56
     poffible
    1.56
     myſelf
    1.53
     Diſ
    1.52
     doubtnut
    1.52
     uſed
    1.45
     Anſ
    1.44
     Monfieur
    1.44
     raiſ
    1.43
    Act Density 1.255%

    No Known Activations