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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    metis
    -0.07
    bin
    -0.07
    lerdi
    -0.06
     Aş
    -0.06
    써
    -0.06
    integer
    -0.06
     didnt
    -0.06
    BIN
    -0.06
     ί
    -0.06
    stdint
    -0.06
    POSITIVE LOGITS
     Nath
    0.06
    repid
    0.06
     Sommer
    0.06
     :↵
    0.06
     unnatural
    0.06
     ['
    0.06
     Dmitry
    0.06
     pioneers
    0.06
    ...";↵
    0.06
    Γ
    0.06
    Act Density 0.000%

    No Known Activations