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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orca
    -0.07
     nostro
    -0.07
     Mama
    -0.07
    u
    -0.06
     frustrated
    -0.06
    recur
    -0.06
     poder
    -0.06
    ovaného
    -0.06
     u
    -0.06
    878
    -0.06
    POSITIVE LOGITS
    .SizeType
    0.07
    층의
    0.07
    TextStyle
    0.07
    ワー
    0.07
    度
    0.07
    porate
    0.06
     폐
    0.06
     度
    0.06
    .Dot
    0.06
     LinearLayoutManager
    0.06
    Act Density 0.012%

    No Known Activations