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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...
    -0.08
     নিজেদের
    -0.08
     indeed
    -0.08
     있습니다
    -0.08
    었습니다
    -0.08
    。但是
    -0.07
    IPMENT
    -0.07
    입니다
    -0.07
     LGBTQ
    -0.07
     ತಮ್ಮ
    -0.07
    POSITIVE LOGITS
     منهم
    0.10
     cava
    0.09
     conj
    0.09
     especificamente
    0.09
     symbolizes
    0.08
     infamous
    0.08
     darr
    0.08
     منها
    0.08
     moni
    0.08
     CLK
    0.08
    Act Density 0.169%

    No Known Activations