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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ulation"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Número
    -0.06
     projects
    -0.06
    лися
    -0.06
    标准
    -0.06
    planes
    -0.06
    Cursor
    -0.06
     screen
    -0.06
     Standard
    -0.06
     jouer
    -0.06
     чет
    -0.06
    POSITIVE LOGITS
    �
    0.07
    �
    0.07
     neglect
    0.07
     目
    0.06
    ultimate
    0.06
    \Requests
    0.06
    �
    0.06
     Σεπ
    0.06
     corros
    0.06
     ดาว
    0.06
    Act Density 0.002%

    No Known Activations