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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operators

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

    Mathematical expressions or equations

    np_acts-logits-general · gemini-2.0-flash

    variable assignments "let" "suppose"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -1.10
     A
    -1.01
     la
    -0.99
     et
    -0.98
     d
    -0.98
     l
    -0.97
     de
    -0.97
     [
    -0.96
     _
    -0.96
     qu
    -0.96
    POSITIVE LOGITS
     itſelf
    1.99
     myſelf
    1.92
     Monfieur
    1.80
     ་་
    1.80
     pleaſure
    1.75
    ſelf
    1.70
    ſelves
    1.70
     Anſ
    1.67
     Shakspeare
    1.66
     Efq
    1.65
    Act Density 0.537%

    No Known Activations