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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs and data handling patterns

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

    Code, values, or symbols

    np_acts-logits-general · gemini-2.0-flash

    code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.62
     
    -0.60
     has
    -0.55
     re
    -0.54
     "
    -0.53
     Ver
    -0.53
     pre
    -0.52
     (
    -0.52
     an
    -0.51
     have
    -0.50
    POSITIVE LOGITS
     pleaſure
    1.19
     houſe
    1.17
     Majefty
    1.14
     myſelf
    1.12
     purpoſe
    1.11
     Houſe
    1.08
     Anſ
    1.08
     Chriftian
    1.07
     CreateTagHelper
    1.06
     autorytatywna
    1.06
    Act Density 0.364%

    No Known Activations