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

    Neuronpedia

    INDEX
    Explanations

    Informal conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اط
    -0.08
     backlight
    -0.07
     أد
    -0.07
    那里
    -0.07
    oran
    -0.06
    Sounds
    -0.06
     KH
    -0.06
    :boolean
    -0.06
     filters
    -0.06
     bike
    -0.06
    POSITIVE LOGITS
    Refer
    0.07
    .UInt
    0.07
     tipping
    0.07
    .onclick
    0.07
     псих
    0.06
    -----↵↵
    0.06
    (big
    0.06
    ***↵↵
    0.06
    ={{
    0.06
     }),↵↵
    0.06
    Act Density 0.067%

    No Known Activations