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

    Neuronpedia

    INDEX
    Explanations

    technology's impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    男子
    -0.08
    BUM
    -0.08
     nayo
    -0.08
    yo
    -0.08
    nz
    -0.08
    Raz
    -0.08
     vegetable
    -0.08
    Apparently
    -0.08
    “I
    -0.08
     さん
    -0.08
    POSITIVE LOGITS
     सक्षम
    0.13
     unprecedented
    0.12
     Facilit
    0.12
     facilita
    0.11
     facilitar
    0.11
     facilite
    0.11
     enabling
    0.11
     faciliter
    0.11
     enable
    0.11
     enables
    0.11
    Act Density 0.106%

    No Known Activations