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

    Neuronpedia

    INDEX
    Explanations

    dependent relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vic
    -0.08
     immoral
    -0.07
     vic
    -0.07
    İL
    -0.07
     CI
    -0.06
    幸福
    -0.06
    哦
    -0.06
    шир
    -0.06
    葡
    -0.06
     stil
    -0.06
    POSITIVE LOGITS
     accr
    0.06
    __)
    0.06
    consts
    0.06
     exceeds
    0.06
     quickest
    0.06
    /components
    0.06
    ….↵↵
    0.06
    ceiver
    0.06
    (dAtA
    0.06
    experimental
    0.06
    Act Density 0.007%

    No Known Activations