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
    Rand
    -0.07
    :)↵
    -0.06
     critics
    -0.06
    444
    -0.06
     ап
    -0.06
    win
    -0.06
     trấn
    -0.06
     piles
    -0.06
    RelativeLayout
    -0.06
    _Comm
    -0.06
    POSITIVE LOGITS
     sprinkle
    0.07
    opard
    0.07
    07
    0.07
    .son
    0.07
    ION
    0.06
    HOST
    0.06
     shorter
    0.06
     sons
    0.06
    duct
    0.06
    -backend
    0.06
    Act Density 0.090%

    No Known Activations