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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filmed
    -0.07
    433
    -0.07
    (selected
    -0.07
    人类
    -0.06
     připrav
    -0.06
    iyordu
    -0.06
     kötü
    -0.06
    动物
    -0.06
    uido
    -0.06
     Thornton
    -0.06
    POSITIVE LOGITS
     POSSIBILITY
    0.06
     ΑΓ
    0.06
    мат
    0.06
     Esper
    0.06
    nev
    0.06
    ertext
    0.06
     Hardware
    0.06
     Dip
    0.06
     Christina
    0.06
     reefs
    0.06
    Act Density 0.012%

    No Known Activations