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

    Neuronpedia

    INDEX
    Explanations

    account information and help requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेटेड
    0.34
     topologies
    0.33
     acceleration
    0.32
     topological
    0.32
    ース
    0.32
     riparian
    0.32
     বলেছি
    0.31
     chub
    0.31
     നിങ്ങൾ
    0.31
    れない
    0.31
    POSITIVE LOGITS
     internes
    0.37
     administrativas
    0.37
     interne
    0.35
     administrativos
    0.35
    狐
    0.35
     tutur
    0.34
     happily
    0.34
     senden
    0.34
     administrativa
    0.34
     housekeeping
    0.33
    Act Density 0.094%

    No Known Activations