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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    layouts
    -0.08
    .adapter
    -0.07
    agram
    -0.07
    гот
    -0.07
     instit
    -0.06
    AIT
    -0.06
    .show
    -0.06
    roman
    -0.06
     phoneNumber
    -0.06
     timer
    -0.06
    POSITIVE LOGITS
    (Util
    0.07
     Diego
    0.06
     faithful
    0.06
    Ey
    0.06
    .Formatting
    0.06
     LSB
    0.06
     Rt
    0.06
     "")
↵
    0.06
     Herrera
    0.06
     DISABLE
    0.06
    Act Density 0.031%

    No Known Activations