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

    Neuronpedia

    INDEX
    Explanations

    delivery and functionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     algorithms
    0.42
    algorithms
    0.39
     Domains
    0.38
     sobres
    0.38
     fortr
    0.38
     hallmarks
    0.37
     JSON
    0.37
    しやすい
    0.37
     खूब
    0.37
     climbed
    0.36
    POSITIVE LOGITS
     circumvent
    0.59
     firepower
    0.55
     ലഭ്യ
    0.55
     obtain
    0.54
     availability
    0.54
    を実現
    0.54
     obtaining
    0.53
    availability
    0.52
     functionality
    0.50
     footwear
    0.50
    Act Density 0.034%

    No Known Activations