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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ajas
    -0.07
    +f
    -0.07
     Bis
    -0.06
     Bek
    -0.06
     енерг
    -0.06
     acquisitions
    -0.06
     ways
    -0.06
     Ways
    -0.06
    _paper
    -0.06
     carriage
    -0.06
    POSITIVE LOGITS
     دولتی
    0.07
    独
    0.07
    .equal
    0.07
     того
    0.06
    _PB
    0.06
    ')↵↵
    0.06
    ITION
    0.06
    );↵↵
    0.06
    summer
    0.06
    .Hosting
    0.06
    Act Density 0.021%

    No Known Activations