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

    Neuronpedia

    INDEX
    Explanations

    compact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (action
    -0.07
    보험
    -0.06
     diary
    -0.06
    吨
    -0.06
    éd
    -0.06
    �始化
    -0.06
    ��取
    -0.06
    Ơ
    -0.06
     Aid
    -0.06
    SPORT
    -0.06
    POSITIVE LOGITS
     XK
    0.07
     intellectually
    0.06
    تق
    0.06
     내
    0.06
    uropean
    0.06
     charming
    0.06
     gesch
    0.06
    lsa
    0.06
     kapit
    0.06
     Iraq
    0.06
    Act Density 0.001%

    No Known Activations