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

    Neuronpedia

    INDEX
    Explanations

    skills and knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hé
    -0.07
    Degree
    -0.06
     Nikola
    -0.06
    澂
    -0.06
     derives
    -0.06
    骼
    -0.06
     Andersen
    -0.06
    诞生
    -0.06
     Deb
    -0.06
     unveiling
    -0.06
    POSITIVE LOGITS
    .writeFileSync
    0.07
    SW
    0.07
     horizontally
    0.07
    (square
    0.07
     quietly
    0.07
     poem
    0.06
    boy
    0.06
    .""
    0.06
    	protected
    0.06
    	foreach
    0.06
    Act Density 0.092%

    No Known Activations