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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and syntax

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

    latex math expressions like `\mathbf` and `\left`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.55
     pleaſure
    -0.54
     poffible
    -0.52
     uſed
    -0.51
     purpoſe
    -0.44
     étoit
    -0.44
    bootstrapcdn
    -0.44
    RotationOrder
    -0.44
    ynomial
    -0.44
    UnknownFields
    -0.44
    POSITIVE LOGITS
    ="'.$
    0.47
     <>",
    0.46
     <<<<<<<<<<<<<<
    0.46
    @[+][
    0.45
     formally
    0.40
     <",
    0.39
     er
    0.38
     MenuView
    0.36
    ">',
    0.36
    httphttps
    0.35
    Act Density 0.103%

    No Known Activations