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

    Neuronpedia

    INDEX
    Explanations

    Code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pulp
    -0.07
    _Box
    -0.07
    scribed
    -0.07
     Pty
    -0.06
    dead
    -0.06
    MENU
    -0.06
     lesser
    -0.06
     financed
    -0.06
    alars
    -0.06
    .reload
    -0.06
    POSITIVE LOGITS
     برخی
    0.07
     الناس
    0.06
     bullied
    0.06
    (jq
    0.06
     ustanov
    0.06
     $_[
    0.06
    _OPTIONS
    0.06
     dazz
    0.06
     summarized
    0.06
    entanyl
    0.06
    Act Density 0.013%

    No Known Activations