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

    Neuronpedia

    INDEX
    Explanations

    Li

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     audiences
    -0.07
    $n
    -0.06
     otros
    -0.06
     fourth
    -0.06
    цы
    -0.06
     Triumph
    -0.06
    udades
    -0.06
     unf
    -0.06
     increase
    -0.06
    _activation
    -0.06
    POSITIVE LOGITS
    _Timer
    0.07
     wirk
    0.07
     نار
    0.07
    ровер
    0.07
    わけ
    0.07
    ayi
    0.07
    braska
    0.07
    ivor
    0.07
     Bankası
    0.07
     fileInfo
    0.06
    Act Density 0.017%

    No Known Activations