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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عام
    -0.07
     sire
    -0.06
    Num
    -0.06
    .Body
    -0.06
     categories
    -0.06
     Chester
    -0.06
    Century
    -0.06
    	Server
    -0.06
    Down
    -0.06
    ака
    -0.06
    POSITIVE LOGITS
    stantial
    0.07
    creates
    0.06
     construed
    0.06
     Ook
    0.06
    description
    0.06
     strict
    0.06
    /")↵
    0.06
    .feedback
    0.06
    】【
    0.06
     swirling
    0.06
    Act Density 0.078%

    No Known Activations