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

    Neuronpedia

    INDEX
    Explanations

    sys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canadian
    -0.07
     isNew
    -0.07
     deluxe
    -0.07
     norske
    -0.07
    .Publish
    -0.07
     Higher
    -0.07
    Atomic
    -0.07
    apsible
    -0.07
    (Grid
    -0.07
     unlocked
    -0.07
    POSITIVE LOGITS
    ▫
    0.09
    𫫇
    0.07
    ~~~~
    0.07
    棰
    0.07
    昧
    0.06
    Auth
    0.06
     can
    0.06
            
    0.06
    穸
    0.06
    ||||
    0.06
    Act Density 0.002%

    No Known Activations