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

    Neuronpedia

    INDEX
    Explanations

    solutions after bottlenecks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CodeableConcept
    0.43
     चयनित
    0.43
     dataset
    0.42
     tribal
    0.42
    ជំ
    0.41
     model
    0.41
     novel
    0.41
     conformations
    0.41
     plots
    0.41
     cutter
    0.40
    POSITIVE LOGITS
    ᓘ
    0.46
     Berl
    0.45
     spiaggia
    0.45
    vezet
    0.43
    滀
    0.43
    僄
    0.42
    istors
    0.42
     nonché
    0.41
     Barrington
    0.41
    0.40
    Act Density 0.007%

    No Known Activations