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

    Neuronpedia

    INDEX
    Explanations

    surrounding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pitié
    -0.92
     touristes
    -0.84
     marins
    -0.71
     Grecs
    -0.71
    astify
    -0.70
     enfans
    -0.69
    TagMode
    -0.68
     ouvriers
    -0.67
     varandra
    -0.67
     Juifs
    -0.67
    POSITIVE LOGITS
     
    0.59
     into
    0.57
     with
    0.56
     it
    0.56
     ‘
    0.54
     “
    0.50
     With
    0.49
     the
    0.48
     Get
    0.48
     via
    0.48
    Act Density 0.025%

    No Known Activations