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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()],
    -0.07
     infl
    -0.07
     represents
    -0.07
     Pt
    -0.07
     hazard
    -0.07
     І
    -0.07
     ffi
    -0.06
     چ
    -0.06
    (tp
    -0.06
    ्षण
    -0.06
    POSITIVE LOGITS
    固定
    0.06
    時に
    0.06
    gaben
    0.06
    ้องน
    0.06
    一定
    0.06
    cite
    0.06
     아�
    0.06
     yüksek
    0.06
     kob
    0.06
    omed
    0.06
    Act Density 0.004%

    No Known Activations