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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choke
    -0.07
    PROPERTY
    -0.06
    	className
    -0.06
     захворювання
    -0.06
    recur
    -0.06
    коз
    -0.06
    SKIP
    -0.06
    jezd
    -0.06
    apers
    -0.06
     بهترین
    -0.06
    POSITIVE LOGITS
     ALT
    0.13
     Decre
    0.07
    \',
    0.07
    ALT
    0.07
     Alb
    0.07
    异
    0.07
     Dump
    0.06
    .Interfaces
    0.06
    .Free
    0.06
     До
    0.06
    Act Density 0.004%

    No Known Activations