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

    Neuronpedia

    INDEX
    Explanations

    code, paths, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اذا
    -0.08
     отрим
    -0.07
    arrow
    -0.06
     runaway
    -0.06
     현재
    -0.06
     dout
    -0.06
     intrig
    -0.06
     вже
    -0.06
    єш
    -0.06
    razione
    -0.06
    POSITIVE LOGITS
     plank
    0.07
     Robin
    0.07
    Robin
    0.06
    goals
    0.06
    Art
    0.06
    Inputs
    0.06
    스토
    0.06
    uy
    0.06
    Laura
    0.06
    ERROR
    0.06
    Act Density 0.000%

    No Known Activations