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

    Neuronpedia

    INDEX
    Explanations

    external links and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ší
    -0.07
     MBA
    -0.06
    SEQUENTIAL
    -0.06
     Cake
    -0.06
     Cheer
    -0.06
    有点
    -0.06
     cảnh
    -0.06
    ci
    -0.06
     farm
    -0.06
    تمر
    -0.06
    POSITIVE LOGITS
    <X
    0.07
    III
    0.07
    にして
    0.07
    did
    0.06
    訳
    0.06
     Hernandez
    0.06
     iii
    0.06
     III
    0.06
    ΑΤ
    0.06
    不足
    0.06
    Act Density 0.009%

    No Known Activations