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

    Neuronpedia

    INDEX
    Explanations

    exclamatory expressions and emotional reactions

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

    debug1:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.66
     Roskov
    -0.65
     protoimpl
    -0.62
     Italijani
    -0.59
    ThroughAttribute
    -0.59
    rrggbb
    -0.55
    NameInMap
    -0.53
    новништво
    -0.52
     సౌకర్య
    -0.51
     linkovi
    -0.50
    POSITIVE LOGITS
     gang
    0.44
     es
    0.39
    inerja
    0.35
    LabelTagHelper
    0.35
     dis
    0.34
    ReferenceEquals
    0.34
     ro
    0.32
    ularity
    0.32
    beginTransaction
    0.32
     py
    0.31
    Act Density 0.040%

    No Known Activations