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

    Neuronpedia

    INDEX
    Explanations

    the beginning of textual entries or sections indicating new content

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

    Follows "since," "of," "is," or "because"

    np_acts-logits-general · gemini-2.0-flash

    code and documentation structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Przypisy
    -0.67
     utafitiHapana
    -0.65
     OFDb
    -0.60
    oredCriteria
    -0.60
     esternos
    -0.57
    Personendaten
    -0.49
     crossorigin
    -0.49
     nakalista
    -0.48
    oa̍t
    -0.47
    EndProject
    -0.47
    POSITIVE LOGITS
    CJK
    0.94
    RetentionPolicy
    0.64
     jadx
    0.62
    WriteTagHelper
    0.59
     InputDecoration
    0.58
    AnchorStyles
    0.55
    ")){
    0.54
    validates
    0.54
     CJK
    0.52
    RSpec
    0.51
    Act Density 0.029%

    No Known Activations