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

    Neuronpedia

    INDEX
    Explanations

    square roots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -paid
    -0.08
     willing
    -0.07
     fryer
    -0.07
     productions
    -0.07
     mayonnaise
    -0.07
     Hector
    -0.07
    /all
    -0.07
     Bleu
    -0.07
     consenting
    -0.07
     grade
    -0.07
    POSITIVE LOGITS
    跨度
    0.09
    Approx
    0.09
     approximate
    0.08
     aproxim
    0.08
     approximately
    0.08
     الشاشة
    0.08
     rough
    0.08
     Approx
    0.08
     roughly
    0.08
    (register
    0.08
    Act Density 0.021%

    No Known Activations