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

    Neuronpedia

    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _packages
    -0.07
     spíše
    -0.07
     있는데
    -0.07
    instructions
    -0.07
     مساحت
    -0.07
     학
    -0.06
     JV
    -0.06
     nurses
    -0.06
     Мар
    -0.06
     gift
    -0.06
    POSITIVE LOGITS
    -basket
    0.07
     」
    0.07
    影
    0.06
     سلس
    0.06
    044
    0.06
     Thomson
    0.06
    あり
    0.06
    _FUN
    0.06
     페
    0.06
     problematic
    0.06
    Act Density 0.011%

    No Known Activations