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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _epsilon
    -0.07
     Caroline
    -0.06
    ,node
    -0.06
    	animation
    -0.06
    _ELEMENTS
    -0.06
     Colony
    -0.06
    	update
    -0.06
     PROPERTY
    -0.06
     groundbreaking
    -0.06
     /></
    -0.06
    POSITIVE LOGITS
     Poverty
    0.07
     �
    0.07
     کاهش
    0.07
     readable
    0.06
     aquel
    0.06
     زمان
    0.06
    ipl
    0.06
     환경
    0.06
    .st
    0.06
     osoby
    0.06
    Act Density 0.021%

    No Known Activations