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

    Neuronpedia

    INDEX
    Explanations

    adjust and risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manageable
    -0.07
     amazingly
    -0.07
     adap
    -0.07
     astonishing
    -0.07
     enough
    -0.07
    MMMM
    -0.07
    一件
    -0.07
    仿佛
    -0.06
    とても
    -0.06
    讓他們
    -0.06
    POSITIVE LOGITS
     הילד
    0.07
    (y
    0.07
     Rolex
    0.07
    >s
    0.07
     careers
    0.07
     primo
    0.07
    ybrid
    0.07
     rookie
    0.07
     falling
    0.06
     calculator
    0.06
    Act Density 0.063%

    No Known Activations