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

    Neuronpedia

    INDEX
    Explanations

    samaritans, sampling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    营养
    0.45
     those
    0.42
     nutritional
    0.42
     nutri
    0.40
    ція
    0.40
    ాలా
    0.40
     artificial
    0.39
     surprise
    0.39
     nutric
    0.39
     perish
    0.39
    POSITIVE LOGITS
    Sampling
    0.66
     sampler
    0.65
     Sampling
    0.61
    sampler
    0.59
     sam
    0.57
    Sampler
    0.57
     Sam
    0.57
    Sam
    0.57
     Sample
    0.56
     SAM
    0.55
    Act Density 0.010%

    No Known Activations