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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YST
    -0.07
    кі
    -0.07
    pack
    -0.07
    ubb
    -0.06
    _ERR
    -0.06
    аний
    -0.06
     cyst
    -0.06
    (no
    -0.06
    важ
    -0.06
    มหาว
    -0.06
    POSITIVE LOGITS
     Brig
    0.07
     přem
    0.06
     jose
    0.06
     répond
    0.06
    提交
    0.06
     Carroll
    0.06
     bitwise
    0.06
     Nicar
    0.06
    .eof
    0.06
     éc
    0.06
    Act Density 0.058%

    No Known Activations