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

    Neuronpedia

    INDEX
    Explanations

    substituting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сторону
    -0.07
     RAW
    -0.07
     非
    -0.07
    非
    -0.06
    IALOG
    -0.06
     Spit
    -0.06
     artist
    -0.06
     Douglas
    -0.06
     Walter
    -0.06
     딸
    -0.06
    POSITIVE LOGITS
     Máy
    0.07
     peu
    0.07
    monary
    0.07
    	printk
    0.07
     Gas
    0.07
    ypes
    0.06
    (id
    0.06
     Poz
    0.06
    Launching
    0.06
    %A
    0.06
    Act Density 0.007%

    No Known Activations