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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expr
    -0.07
     dela
    -0.06
     Michaels
    -0.06
    _span
    -0.06
    ์ว
    -0.06
     radius
    -0.06
     被
    -0.06
     Undert
    -0.06
     кат
    -0.06
    anges
    -0.06
    POSITIVE LOGITS
    帝
    0.07
    fontWeight
    0.07
     theft
    0.07
    "]))↵
    0.06
    -led
    0.06
    ��
    0.06
     undesirable
    0.06
    росто
    0.06
    }}}
    0.06
    ้านด
    0.06
    Act Density 0.059%

    No Known Activations