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

    Neuronpedia

    INDEX
    Explanations

    html and css code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    檐
    0.44
     honorary
    0.40
     admin
    0.39
    簷
    0.39
     weather
    0.38
    ᄍ
    0.38
     hello
    0.37
     Flower
    0.37
     तेलु
    0.37
     flowers
    0.36
    POSITIVE LOGITS
     Obituary
    0.38
    pic
    0.37
    Alignment
    0.37
    туры
    0.37
    Following
    0.36
     tử
    0.36
    Pic
    0.36
    burgh
    0.35
    function
    0.35
    cargar
    0.35
    Act Density 0.001%

    No Known Activations