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

    Neuronpedia

    INDEX
    Explanations

    paid rights/permissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NumberOf
    -0.07
    ([('
    -0.07
     baked
    -0.07
    USR
    -0.07
     [[[
    -0.06
     <<
    -0.06
     acknowledgment
    -0.06
     identifying
    -0.06
    Cap
    -0.06
    了解
    -0.06
    POSITIVE LOGITS
    ``,
    0.07
     ():
    0.07
    =models
    0.06
     fortune
    0.06
     necessarily
    0.06
    categories
    0.06
     Theme
    0.06
     dorm
    0.06
    GUI
    0.06
    risk
    0.06
    Act Density 0.136%

    No Known Activations