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

    Neuronpedia

    INDEX
    Explanations

    references to game players and their turn sequence

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

    player turn or start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funkcjon
    -0.37
     bahía
    -0.35
     aşk
    -0.34
    GeneratedCode
    -0.32
     cartera
    -0.31
     catedral
    -0.31
     embarazada
    -0.30
    rungsseite
    -0.30
     Stufe
    -0.30
     Begleitung
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.93
    MethodManager
    0.71
     oprot
    0.71
    transQ
    0.69
    AddTagHelper
    0.64
     StringTokenizer
    0.62
    bufio
    0.61
    awtextra
    0.60
     Vikipedi
    0.60
     好文分享
    0.56
    Act Density 0.131%

    No Known Activations