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

    Neuronpedia

    INDEX
    Explanations

    Diverse texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loader
    -0.06
     calculus
    -0.06
     Fav
    -0.06
     sovereign
    -0.06
    TOP
    -0.06
    \Extension
    -0.06
     glory
    -0.06
     lazy
    -0.06
     actors
    -0.06
    meal
    -0.06
    POSITIVE LOGITS
    weep
    0.07
     opport
    0.06
    提出
    0.06
    imm
    0.06
     Flatten
    0.06
     reclaimed
    0.06
     закон
    0.06
     Vermont
    0.06
     답
    0.06
    plt
    0.06
    Act Density 0.000%

    No Known Activations