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

    Neuronpedia

    INDEX
    Explanations

    home maintenance/problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    builders
    -0.07
     feathers
    -0.07
     Louis
    -0.07
    acre
    -0.07
    ationship
    -0.07
    ’acc
    -0.06
    (chip
    -0.06
     Arithmetic
    -0.06
     Gaussian
    -0.06
     aviation
    -0.06
    POSITIVE LOGITS
    ="{!!
    0.07
     BoxFit
    0.07
    -wsj
    0.06
    іл
    0.06
    Ticker
    0.06
     Extract
    0.06
     Coordinates
    0.06
    587
    0.06
    /sl
    0.06
    .ge
    0.06
    Act Density 0.048%

    No Known Activations