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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stamp
    -0.07
     entfer
    -0.07
    Monday
    -0.06
    wer
    -0.06
    -town
    -0.06
    pais
    -0.06
    ANGUAGE
    -0.06
    ()!=
    -0.06
    DataProvider
    -0.06
    لیت
    -0.06
    POSITIVE LOGITS
     FORMAT
    0.07
     electricity
    0.06
     exhausted
    0.06
    	Double
    0.06
     Checkbox
    0.06
     дити
    0.06
     predictions
    0.06
     precarious
    0.06
    isActive
    0.06
    ��
    0.06
    Act Density 0.014%

    No Known Activations