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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (PRO
    -0.07
     Saudis
    -0.07
     Định
    -0.07
    隨
    -0.06
     Snowden
    -0.06
     Nations
    -0.06
    <R
    -0.06
    연구
    -0.06
    -track
    -0.06
     disclose
    -0.06
    POSITIVE LOGITS
     итог
    0.07
     ию
    0.06
     mar
    0.06
    _QU
    0.06
    高速
    0.06
    .blit
    0.06
    olicy
    0.06
    ışma
    0.06
    dg
    0.06
    κας
    0.06
    Act Density 0.017%

    No Known Activations