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

    Neuronpedia

    INDEX
    Explanations

    coding and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Archbishop
    -0.07
     mirrors
    -0.07
    .Float
    -0.07
    MainMenu
    -0.06
     statue
    -0.06
     Hyderabad
    -0.06
     mountains
    -0.06
     trimest
    -0.06
     �
    -0.06
    Các
    -0.06
    POSITIVE LOGITS
    (User
    0.07
    BB
    0.07
     número
    0.06
    ("#
    0.06
    $↵↵
    0.06
    .viewport
    0.06
    User
    0.06
     '#'
    0.06
    awah
    0.06
     Motorola
    0.06
    Act Density 0.000%

    No Known Activations