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

    Neuronpedia

    INDEX
    Explanations

    Combinatorial/mathematical designs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sass
    -0.08
    adhi
    -0.08
     tensorflow
    -0.08
     Aw
    -0.08
     confrontation
    -0.08
     Sass
    -0.08
     Flow
    -0.08
     relocation
    -0.08
    _flow
    -0.08
     diap
    -0.07
    POSITIVE LOGITS
     систему
    0.09
    .cluster
    0.09
    .record
    0.08
     systematically
    0.08
    献
    0.08
     множество
    0.08
    зо
    0.08
     subsets
    0.08
     invit
    0.08
    重复
    0.08
    Act Density 0.019%

    No Known Activations