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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (account
    -0.08
     preg
    -0.07
     except
    -0.07
     осіб
    -0.06
     Right
    -0.06
     uranium
    -0.06
     interact
    -0.06
    ивать
    -0.06
    _MARKER
    -0.06
     ges
    -0.06
    POSITIVE LOGITS
    clc
    0.07
    "
↵
↵
↵
    0.06
     Rwanda
    0.06
     CORPOR
    0.06
    amaha
    0.06
    ализации
    0.06
    !“↵↵
    0.06
    ）。↵↵
    0.06
     renamed
    0.06
    (),'
    0.06
    Act Density 0.046%

    No Known Activations