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

    Neuronpedia

    INDEX
    Explanations

    elements associated with code structures, particularly those involving variable assignments and function calls in programming

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

    Code and markup language fragments

    np_acts-logits-general · gemini-2.0-flash

    As you can see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.69
    ?
    -0.63
     for
    -0.61
    :
    -0.59
    .
    -0.57
     by
    -0.57
    -
    -0.55
     Here
    -0.53
     As
    -0.53
     in
    -0.53
    POSITIVE LOGITS
     myſelf
    0.93
     reaſon
    0.93
     pleaſure
    0.92
     Majefty
    0.91
     leſs
    0.88
     purpoſe
    0.88
     theſe
    0.87
    this
    0.87
     ſche
    0.86
     Anſ
    0.84
    Act Density 0.037%

    No Known Activations