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

    Neuronpedia

    INDEX
    Explanations

    There is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incentive
    0.47
     alfabeto
    0.45
     karoti
    0.42
    ਾਨੂੰ
    0.42
     alman
    0.40
     pourcentage
    0.40
     hangover
    0.40
     сотрудни
    0.39
     изготовления
    0.39
    ENTY
    0.39
    POSITIVE LOGITS
     species
    0.46
     Species
    0.46
    pecies
    0.43
    Species
    0.43
     new
    0.41
     narrow
    0.41
     Saying
    0.41
    특별
    0.40
    species
    0.40
     planet
    0.39
    Act Density 0.004%

    No Known Activations