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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and software development

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

    after specific technical terms

    np_acts-logits-general · gemini-2.0-flash

    correction, increase, contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     […]
    -1.94
    ↵
    -1.89
    ↵↵
    -1.55
    <eos>
    -1.50
     [...]
    -1.41
    ,...
    -1.24
    […]
    -1.24
    [...]
    -1.20
     =
    -1.19
    ',...
    -1.17
    POSITIVE LOGITS
    setVerticalGroup
    0.59
    帖最后由
    0.56
    TextEditing
    0.55
    μιουργ
    0.55
    ValueGeneration
    0.54
    ChildScrollView
    0.54
     NSMutable
    0.51
     LoginComponent
    0.50
    selves
    0.48
    EntityFramework
    0.48
    Act Density 0.964%

    No Known Activations