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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vier
    -0.07
    .cover
    -0.06
             
    -0.06
    vis
    -0.06
     )))
    -0.06
    (bus
    -0.06
     Nisan
    -0.06
     ""))↵
    -0.06
     Burnett
    -0.06
    Adds
    -0.06
    POSITIVE LOGITS
     Reminder
    0.07
    .temperature
    0.06
    /mod
    0.06
     الاح
    0.06
     Timeline
    0.06
    이크
    0.06
     рок
    0.06
    CREASE
    0.06
    یم
    0.06
     نمودار
    0.06
    Act Density 0.025%

    No Known Activations