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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions, indicating structural elements of formulas and inequalities

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

    Mathematical or scientific expressions containing vertical bars

    np_acts-logits-general · gemini-2.0-flash

    | followed by math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FontStyle
    -0.63
    tagext
    -0.61
    (")");
    -0.56
    GeneratedValue
    -0.56
    ensement
    -0.55
    ekš
    -0.54
     nawr
    -0.54
    ::-
    -0.54
    oneofs
    -0.53
    akon
    -0.52
    POSITIVE LOGITS
     purpoſe
    0.96
     auffi
    0.93
    .|
    0.93
     myſelf
    0.92
    +|
    0.92
     Jefus
    0.91
     $|
    0.90
     itſelf
    0.88
     $|\
    0.87
    ]|
    0.87
    Act Density 0.202%

    No Known Activations