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

    Neuronpedia

    INDEX
    Explanations

    Chess knight moves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    品質
    -0.08
     ethnic
    -0.07
     unn
    -0.07
     fragrances
    -0.07
     indispensables
    -0.07
     antioxidant
    -0.07
     fragrance
    -0.07
     होंगे
    -0.07
    .Please
    -0.07
     informeren
    -0.07
    POSITIVE LOGITS
    规则
    0.10
     Rule
    0.10
    -rule
    0.09
     regras
    0.09
    规定
    0.09
     RULE
    0.09
     Rules
    0.09
     rules
    0.09
     rule
    0.08
     Slav
    0.08
    Act Density 0.048%

    No Known Activations