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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :num
    -0.07
    ованих
    -0.07
    -var
    -0.06
    ]].
    -0.06
     空
    -0.06
     droits
    -0.06
    -In
    -0.06
    上的
    -0.06
    ीसर
    -0.06
    -air
    -0.06
    POSITIVE LOGITS
    نویس
    0.07
     Wet
    0.06
     eBay
    0.06
     horrend
    0.06
    Anything
    0.06
     CASCADE
    0.06
    uge
    0.06
            ↵
    0.06
    Segments
    0.06
     withdrawn
    0.06
    Act Density 0.003%

    No Known Activations