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

    Neuronpedia

    INDEX
    Explanations

    conclusive phrases that indicate summation or final statements in a discussion

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

    Text followed by "Finally"

    np_acts-logits-general · gemini-2.0-flash

    introduces concluding remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.83
    WireFormatLite
    -0.81
    InjectAttribute
    -0.72
     FetchType
    -0.71
    Portale
    -0.67
     ?"
    -0.67
     ?”
    -0.67
     OnTriggerEnter
    -0.66
    UrlResolution
    -0.65
    quiao
    -0.64
    POSITIVE LOGITS
    Obrázky
    0.58
     there
    0.58
    ,
    0.49
     مشين
    0.48
     if
    0.47
     estimés
    0.47
    Since
    0.42
    šech
    0.42
     poche
    0.42
    由於
    0.42
    Act Density 0.335%

    No Known Activations