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

    Neuronpedia

    INDEX
    Explanations

    59

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     script
    -0.08
     lecture
    -0.08
     book
    -0.07
     Book
    -0.07
     act
    -0.07
     look
    -0.07
    Screen
    -0.07
     written
    -0.07
     preach
    -0.07
     loud
    -0.07
    POSITIVE LOGITS
    eba
    0.07
     Az
    0.07
    іли
    0.07
     exemption
    0.07
     FHA
    0.07
     Colo
    0.07
    nelle
    0.07
    นส
    0.06
    ebi
    0.06
    .userdetails
    0.06
    Act Density 0.092%

    No Known Activations