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

    Neuronpedia

    INDEX
    Explanations

    punctuation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Росії
    -0.06
     эф
    -0.06
    ▍▍
    -0.06
    Segoe
    -0.06
     observers
    -0.06
    ěstí
    -0.06
    Crop
    -0.06
     chụp
    -0.05
    -tools
    -0.05
     sucess
    -0.05
    POSITIVE LOGITS
    ίου
    0.07
     konci
    0.07
    .F
    0.06
     Tomas
    0.06
    TRACK
    0.06
     офици
    0.06
    aturally
    0.06
     تا
    0.06
     Chair
    0.06
     Fellow
    0.06
    Act Density 0.011%

    No Known Activations