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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    írk
    -0.07
    کش
    -0.06
    औ
    -0.06
     dram
    -0.06
     characters
    -0.06
     Dimit
    -0.06
     Ciudad
    -0.06
    kg
    -0.06
    UCK
    -0.06
    dec
    -0.05
    POSITIVE LOGITS
    .tasks
    0.07
    .cleaned
    0.07
     포
    0.07
     Thankfully
    0.07
     ​​
    0.06
    .AspNetCore
    0.06
    _aligned
    0.06
    !I
    0.06
    ㅠㅠ
    0.06
    -bold
    0.06
    Act Density 0.011%

    No Known Activations