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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of uncertainty or introspection

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

    words with following phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.60
    \{\\
    -0.54
    ErrUnexpectedEOF
    -0.50
    AccessFile
    -0.50
    Архівовано
    -0.50
     تضيفلها
    -0.48
     automatiques
    -0.48
    AddTagHelper
    -0.48
     ProtoMessage
    -0.47
    umerable
    -0.46
    POSITIVE LOGITS
    awtextra
    0.41
    Latvia
    0.40
    onStop
    0.39
    󠁿
    0.37
     inim
    0.35
    Belfast
    0.35
    TV
    0.35
     AFB
    0.34
    Cair
    0.34
    !...
    0.33
    Act Density 0.091%

    No Known Activations