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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    最初
    -0.07
    belum
    -0.06
     Hungarian
    -0.06
    uncan
    -0.06
     유형
    -0.06
     junction
    -0.06
     spanning
    -0.06
     CARE
    -0.06
     DAG
    -0.06
     GetData
    -0.06
    POSITIVE LOGITS
     ऋ
    0.07
    .fe
    0.07
    loo
    0.07
    (bin
    0.07
     autour
    0.06
     مناس
    0.06
     соот
    0.06
    _tri
    0.06
     Ft
    0.06
    ItemCount
    0.06
    Act Density 0.003%

    No Known Activations