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
     худож
    -0.07
    _HT
    -0.06
     里
    -0.06
    ot
    -0.06
    шин
    -0.06
    (sqrt
    -0.06
    lib
    -0.06
    ipp
    -0.06
    at
    -0.06
    روف
    -0.06
    POSITIVE LOGITS
     커
    0.07
    gles
    0.07
    甲
    0.06
     Thousand
    0.06
    0.06
    .Note
    0.06
     oldValue
    0.06
     Vor
    0.06
    #pragma
    0.06
    =en
    0.06
    Act Density 0.049%

    No Known Activations