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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and expressions of sentiment

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

    internal states and opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Erreferentziak
    -0.44
    
    -0.42
    ariel
    -0.39
     cog
    -0.38
     Hooker
    -0.38
     bug
    -0.37
    Jegyzetek
    -0.37
    otonin
    -0.37
     blanket
    -0.37
     electronic
    -0.37
    POSITIVE LOGITS
    expandindo
    0.72
    webElementXpaths
    0.60
    OGND
    0.59
    دانشنامهٔ
    0.56
     otomatig
    0.54
     ujednoznacz
    0.50
    thâu
    0.48
    فایل‌لار
    0.47
    DataAnnotations
    0.46
     unknownFields
    0.46
    Act Density 0.083%

    No Known Activations