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

    Neuronpedia

    INDEX
    Explanations

    carefully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    除了
    -0.07
    提升
    -0.06
    housing
    -0.06
    altura
    -0.06
    @NoArgsConstructor
    -0.06
     ludicrous
    -0.06
    inema
    -0.06
    631
    -0.06
    date
    -0.06
     linh
    -0.06
    POSITIVE LOGITS
     carefully
    0.13
     careful
    0.08
    ไ
    0.07
     dangerously
    0.07
     연구
    0.07
    JOB
    0.07
    aub
    0.07
     cann
    0.07
     คำ
    0.07
    مع
    0.07
    Act Density 0.007%

    No Known Activations