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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ह
    -0.07
    归
    -0.07
    随
    -0.07
    至
    -0.06
    fore
    -0.06
     contra
    -0.06
    916
    -0.06
     negative
    -0.06
     دور
    -0.06
    Чер
    -0.06
    POSITIVE LOGITS
    OOT
    0.07
    uesta
    0.07
     vengeance
    0.06
    uggestions
    0.06
     �
    0.06
    emodel
    0.06
     Grat
    0.06
     integrates
    0.06
     Eğer
    0.06
     onlar
    0.06
    Act Density 0.017%

    No Known Activations