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

    Neuronpedia

    INDEX
    Explanations

    comments or statements made by influential figures, particularly those that are controversial or provoke public reaction

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

    comments and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     negócio
    -0.26
     mě
    -0.25
     deck
    -0.24
     défa
    -0.23
    Économie
    -0.22
     investis
    -0.22
    talet
    -0.22
     limpio
    -0.21
    τει
    -0.21
     مم
    -0.20
    POSITIVE LOGITS
    AnchorTagHelper
    0.88
    tagHelperRunner
    0.70
    twimg
    0.69
     Majefty
    0.67
     estekak
    0.67
    ScopeManager
    0.67
     ujednoznacz
    0.65
     MatDialog
    0.64
    tagext
    0.63
    \{\\
    0.63
    Act Density 0.315%

    No Known Activations