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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to data processing and extraction

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

    followed by "from" or indicating origin

    np_acts-logits-general · gemini-2.0-flash

    originating from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    by
    -0.47
    <bos>
    -0.42
     createState
    -0.41
    CppMethod
    -0.41
     montanha
    -0.40
    SuppressWarnings
    -0.40
     ismer
    -0.39
    BUG
    -0.39
     طریق
    -0.39
     nisso
    -0.39
    POSITIVE LOGITS
    +#+#
    0.81
     nahilalakip
    0.78
     <<<<<<<<<<<<<<
    0.76
    AddTagHelper
    0.74
    tagHelperRunner
    0.71
    AnchorStyles
    0.71
    EndContext
    0.70
    richTextPanel
    0.70
     venons
    0.69
     ostavi
    0.67
    Act Density 0.304%

    No Known Activations