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

    Neuronpedia

    INDEX
    Explanations

    different forms of negation and emphasis in sentences

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.59
    HtmlAttribute
    -0.56
     betweenstory
    -0.49
    ExtendWith
    -0.48
    apunov
    -0.47
    tagHelperRunner
    -0.46
     TextAppearance
    -0.45
    VIAF
    -0.44
    AnchorStyles
    -0.44
    ancestor
    -0.44
    POSITIVE LOGITS
     externi
    0.41
     vectorielle
    0.40
     ostavi
    0.38
     PeEnEo
    0.37
     itſelf
    0.34
    новниш
    0.34
    ValueMap
    0.33
     companies
    0.33
    Kanpo
    0.33
    Pozri
    0.32
    Act Density 0.107%

    No Known Activations