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
     прек
    -0.07
     heads
    -0.07
     miles
    -0.06
    _good
    -0.06
     mop
    -0.06
     kendisi
    -0.06
    .MiddleCenter
    -0.06
    opak
    -0.06
    .StatusBadRequest
    -0.06
    ávka
    -0.06
    POSITIVE LOGITS
     fatalities
    0.07
    column
    0.07
     experimenting
    0.06
     شمالی
    0.06
     Cron
    0.06
     match
    0.06
     Mess
    0.06
    롤
    0.06
     ['#
    0.06
    )",↵
    0.06
    Act Density 0.026%

    No Known Activations