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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     princípios
    -0.08
     basa
    -0.07
     principles
    -0.07
     principios
    -0.07
    Friend
    -0.07
     hortic
    -0.07
     基
    -0.07
     보여
    -0.07
     조
    -0.07
    statt
    -0.07
    POSITIVE LOGITS
     кроме
    0.11
     besides
    0.10
     bisher
    0.10
     imaginable
    0.10
     Guarantee
    0.09
     bislang
    0.09
     الوحيد
    0.09
     einzige
    0.09
     guaranteed
    0.09
    想到
    0.08
    Act Density 0.068%

    No Known Activations