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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dist
    -0.07
    两款
    -0.07
    ($('
    -0.07
     inaccessible
    -0.07
    isset
    -0.07
    anje
    -0.07
    おす
    -0.07
    /tmp
    -0.07
     tako
    -0.07
    icmp
    -0.07
    POSITIVE LOGITS
     hairstyle
    0.08
     Rectangle
    0.07
     Generation
    0.07
     Inner
    0.07
     composed
    0.07
     façon
    0.07
     size
    0.07
    争夺
    0.07
     heir
    0.07
     protection
    0.07
    Act Density 0.021%

    No Known Activations