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
     amount
    -0.06
     Und
    -0.06
    ADO
    -0.06
     distrust
    -0.06
    太阳城
    -0.06
    tant
    -0.06
    氧
    -0.06
     áreas
    -0.06
    Moon
    -0.06
     para
    -0.06
    POSITIVE LOGITS
    ……。
    0.08
     violates
    0.07
    Він
    0.07
    getVar
    0.07
    plays
    0.07
    sut
    0.07
     =======
    0.07
     गत
    0.07
    ...\
    0.07
    entrant
    0.07
    Act Density 0.260%

    No Known Activations