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

    Neuronpedia

    INDEX
    Explanations

    syntax relating to formatted string outputs and error messaging

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

    String formatting with curly braces

    np_acts-logits-general · gemini-2.0-flash

    string formatting with curly braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.53
     “
    -0.53
     only
    -0.46
     «
    -0.42
    נים
    -0.40
    Hist
    -0.40
     
    -0.40
     nothing
    -0.39
    üz
    -0.39
    FLAGS
    -0.39
    POSITIVE LOGITS
    IndentedString
    1.18
    Geplaatst
    1.16
    ValueStyle
    1.14
     autorytatywna
    1.10
    sizeCache
    1.09
    NameInMap
    1.09
     Савезне
    1.09
    findpost
    1.08
    LookAnd
    1.07
    تقاوى
    1.06
    Act Density 0.051%

    No Known Activations