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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    `);↵↵
    -0.06
    황
    -0.06
    Synopsis
    -0.06
    Ix
    -0.06
    (ro
    -0.06
     "\\
    -0.06
    groupBox
    -0.06
    alogy
    -0.06
     زی
    -0.06
     новые
    -0.06
    POSITIVE LOGITS
     deque
    0.06
     funkci
    0.06
    urm
    0.06
     graduated
    0.06
    Insp
    0.06
     Duch
    0.06
     paired
    0.06
    display
    0.06
    -reviewed
    0.06
    rn
    0.06
    Act Density 0.047%

    No Known Activations