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

    Neuronpedia

    INDEX
    Explanations

    race starting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grade
    -0.07
     Magical
    -0.06
    .Batch
    -0.06
     Paso
    -0.06
    妹
    -0.06
     Darling
    -0.06
     nop
    -0.06
    .Test
    -0.06
    原
    -0.06
     aisle
    -0.06
    POSITIVE LOGITS
    authors
    0.07
    .tencent
    0.07
    <Renderer
    0.07
    년에
    0.07
    Ư�
    0.07
     geld
    0.07
     الشركة
    0.07
    (REG
    0.07
    0.06
    cdecl
    0.06
    Act Density 0.101%

    No Known Activations