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

    Neuronpedia

    INDEX
    Explanations

    research paper titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pertaining
    -0.07
     DEM
    -0.07
    .slf
    -0.07
    030
    -0.07
    -playing
    -0.06
     thirst
    -0.06
    	Player
    -0.06
     Marc
    -0.06
     USERS
    -0.06
     Fou
    -0.06
    POSITIVE LOGITS
    [opt
    0.06
    (signature
    0.06
    .coordinates
    0.06
    .usuario
    0.06
    shint
    0.06
     уже
    0.06
     onItemClick
    0.06
     ऑ
    0.06
    adena
    0.06
    (instruction
    0.06
    Act Density 0.055%

    No Known Activations