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

    Neuronpedia

    INDEX
    Explanations

    please

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Intersection
    -0.07
    \Log
    -0.07
    _As
    -0.06
    Dict
    -0.06
    .Dto
    -0.06
     bye
    -0.06
     Logo
    -0.06
    では
    -0.06
    Similar
    -0.06
     instability
    -0.06
    POSITIVE LOGITS
    .Millisecond
    0.06
    'L
    0.06
     Bell
    0.06
     towns
    0.06
     حالت
    0.06
     shoulder
    0.06
    corev
    0.06
     accustomed
    0.06
     GL
    0.06
    "class
    0.06
    Act Density 0.010%

    No Known Activations