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

    Neuronpedia

    INDEX
    Explanations

    commas and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     residences
    0.24
     pabbaj
    0.23
     stressors
    0.23
     climbs
    0.22
     deities
    0.21
     conjugates
    0.21
     grandkids
    0.21
     bedrooms
    0.21
     invas
    0.21
     originality
    0.21
    POSITIVE LOGITS
    岁
    0.21
     corrente
    0.21
     বুলেট
    0.19
    SSS
    0.19
     ukaz
    0.18
     ubr
    0.18
     Interess
    0.18
     Agustín
    0.18
    砥
    0.18
    포
    0.18
    Act Density 0.015%

    No Known Activations