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

    Neuronpedia

    INDEX
    Explanations

    descriptions of property with views

    oai_token-act-pair · gemini-2.0-flash

    geographical features and scenic views

    np_token-act-pair-logits · gpt-4o-mini

    places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .*")]
    -0.47
    kurz
    -0.46
     ✭✭
    -0.44
     usaha
    -0.41
    일
    -0.40
    imarães
    -0.40
     widerrufen
    -0.39
     última
    -0.39
     half
    -0.39
    在地
    -0.39
    POSITIVE LOGITS
     Мексичка
    0.79
    ValueStyle
    0.70
    RenderAtEndOf
    0.69
     pines
    0.69
    URLException
    0.65
    SBATCH
    0.65
    MLLoader
    0.65
     Argentino
    0.63
     whoſe
    0.62
     hills
    0.61
    Act Density 1.141%

    No Known Activations