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

    Neuronpedia

    INDEX
    Explanations

    & Co

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    棪
    0.52
     Rating
    0.50
     Colombeau
    0.50
     Instances
    0.49
     Packing
    0.49
     Juden
    0.48
     Blades
    0.47
    班牙
    0.46
    pits
    0.46
    miers
    0.46
    POSITIVE LOGITS
     x
    0.52
     athlete
    0.48
    resources
    0.47
     audited
    0.47
     sunlight
    0.47
     social
    0.46
     surfaces
    0.46
     sill
    0.46
     published
    0.46
     researched
    0.46
    Act Density 0.000%

    No Known Activations