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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     что
    -0.06
     smell
    -0.06
     bes
    -0.06
     comboBox
    -0.06
    斥
    -0.06
    这篇文章
    -0.06
    oked
    -0.06
    弸
    -0.06
    手臂
    -0.06
    rene
    -0.06
    POSITIVE LOGITS
     Bas
    0.07
     withheld
    0.07
    .STATUS
    0.07
     medios
    0.07
     לוקח
    0.07
    _POINTS
    0.07
    处境
    0.07
     Clean
    0.06
     gén
    0.06
     alternatively
    0.06
    Act Density 0.144%

    No Known Activations