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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мог
    -0.07
    ech
    -0.07
    <small
    -0.06
    /address
    -0.06
    spNet
    -0.06
    иться
    -0.06
    Earlier
    -0.06
    ugi
    -0.06
    。（
    -0.06
     organs
    -0.06
    POSITIVE LOGITS
     veto
    0.08
     Ore
    0.07
     дитини
    0.06
     classNames
    0.06
     '-')↵
    0.06
     deset
    0.06
     Islam
    0.06
    ออนไลน
    0.06
    .Sc
    0.06
    иск
    0.06
    Act Density 0.147%

    No Known Activations