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

    Neuronpedia

    INDEX
    Explanations

    Helping others

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :B
    -0.07
    .brand
    -0.07
     겁니다
    -0.07
    תפו
    -0.07
    _ARB
    -0.07
    ANTITY
    -0.07
    _HINT
    -0.07
     setVisible
    -0.07
     pp
    -0.07
    精品
    -0.07
    POSITIVE LOGITS
    תוכניות
    0.07
    usband
    0.06
    反复
    0.06
    直
    0.06
    啸
    0.06
    𬉼
    0.06
    ها
    0.06
    ⚌
    0.06
    makers
    0.06
    Υ
    0.06
    Act Density 0.061%

    No Known Activations