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

    Neuronpedia

    INDEX
    Explanations

    action/methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	to
    -0.07
     as
    -0.07
     والأ
    -0.06
     ani
    -0.06
    clar
    -0.06
     RS
    -0.06
     axes
    -0.06
     crispy
    -0.06
    Until
    -0.06
     globals
    -0.06
    POSITIVE LOGITS
     greetings
    0.08
    (heap
    0.07
     underway
    0.07
    .toJSON
    0.06
     setFrame
    0.06
     Москва
    0.06
    relude
    0.06
    鞋
    0.06
    ρέ
    0.06
    urface
    0.06
    Act Density 0.237%

    No Known Activations