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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.96
     still
    -0.92
    still
    -0.89
     fortfarande
    -0.77
     STILL
    -0.77
     Still
    -0.77
    Still
    -0.75
    STILL
    -0.66
     médicaux
    -0.57
     toujours
    -0.55
    POSITIVE LOGITS
     Roskov
    0.78
    didSet
    0.64
     require
    0.63
     exist
    0.61
     occur
    0.59
    CHAFT
    0.59
     await
    0.59
    يكب
    0.58
    SOUNDBITE
    0.57
    JspWriter
    0.56
    Act Density 0.047%

    No Known Activations