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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .w
    -0.07
    .cr
    -0.07
    쓰
    -0.07
     Elegant
    -0.06
     Columns
    -0.06
     iss
    -0.06
    .q
    -0.06
    aul
    -0.06
     Columbus
    -0.06
     nf
    -0.06
    POSITIVE LOGITS
     beraber
    0.08
    `${
    0.06
    ='${
    0.06
    .ToInt
    0.06
    (goal
    0.06
     enamel
    0.06
     basit
    0.06
    (init
    0.06
    BeforeEach
    0.06
    鑑
    0.06
    Act Density 0.019%

    No Known Activations