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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cells
    -0.06
    Aud
    -0.06
    Indicator
    -0.06
    �
    -0.06
     save
    -0.06
     změ
    -0.06
    beg
    -0.06
    дается
    -0.06
     клет
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     -(
    0.07
     Whitney
    0.07
     Literary
    0.07
     ngOn
    0.07
     John
    0.07
     kuchy
    0.07
     jednání
    0.07
    ları
    0.06
    996
    0.06
     /^(
    0.06
    Act Density 0.119%

    No Known Activations