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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Scheme
    -0.07
     cycles
    -0.07
     npm
    -0.06
     since
    -0.06
     收
    -0.06
     opinion
    -0.06
     разі
    -0.06
    Suffix
    -0.06
    (recipe
    -0.06
     So
    -0.06
    POSITIVE LOGITS
    leasing
    0.07
    rou
    0.07
    ЛА
    0.07
    Interpolator
    0.06
    .IDENTITY
    0.06
     Lebanese
    0.06
                             ↵
    0.06
    ätt
    0.06
     surrendered
    0.06
    alty
    0.06
    Act Density 0.017%

    No Known Activations