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

    Neuronpedia

    INDEX
    Explanations

    references to additional files or supplementary materials in research documents

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

    additional file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.68
    Datuak
    -0.60
    tagHelperRunner
    -0.54
    uxxxx
    -0.52
    .*")]
    -0.50
     Administrativna
    -0.50
     Normdatei
    -0.50
     mergeFrom
    -0.49
    PreferredItem
    -0.48
     createState
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.38
    اریخ
    0.36
    osoba
    0.36
    protoc
    0.34
     diagrama
    0.34
     multer
    0.34
     voici
    0.33
     Perdana
    0.33
    bigl
    0.33
    cinfo
    0.33
    Act Density 0.069%

    No Known Activations