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

    Neuronpedia

    INDEX
    Explanations

    dog owner, walking, groom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बैच
    0.43
    üge
    0.41
    adă
    0.40
    槍
    0.40
    Grady
    0.39
    direction
    0.39
    รถ
    0.39
    analysis
    0.38
    ர்
    0.38
    evidence
    0.38
    POSITIVE LOGITS
     paws
    0.59
     породы
    0.55
     figurine
    0.54
    咪
    0.54
     paw
    0.52
     populations
    0.51
     species
    0.51
     breeders
    0.51
     husbandry
    0.51
     population
    0.50
    Act Density 0.038%

    No Known Activations