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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roots
    -0.07
     článku
    -0.07
     وابسته
    -0.06
    	con
    -0.06
     outs
    -0.06
    .ActionListener
    -0.06
    arta
    -0.06
     invaders
    -0.06
    ستم
    -0.06
     mnoh
    -0.06
    POSITIVE LOGITS
     support
    0.07
     přím
    0.06
     Александ
    0.06
    celain
    0.06
    .entrySet
    0.06
    export
    0.06
     Poz
    0.06
    Mask
    0.05
    Serial
    0.05
     prize
    0.05
    Act Density 0.001%

    No Known Activations