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

    Neuronpedia

    INDEX
    Explanations

    choices or decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bubble
    -0.07
    J
    -0.07
     Kar
    -0.07
    SQ
    -0.06
     Appointment
    -0.06
    ZH
    -0.06
     plate
    -0.06
    Letters
    -0.06
     Patton
    -0.06
    ientos
    -0.06
    POSITIVE LOGITS
     overshadow
    0.07
    (gray
    0.07
    ctrine
    0.06
    _phy
    0.06
     Subset
    0.06
    incinn
    0.06
     програ
    0.06
     ارتف
    0.06
    (cli
    0.06
    .Matchers
    0.06
    Act Density 0.098%

    No Known Activations