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

    Neuronpedia

    INDEX
    Explanations

    runner-up, thrift store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ের
    0.40
     postérieures
    0.40
     europäischen
    0.39
    Pyrimidine
    0.39
     Ressourcen
    0.39
     fichiers
    0.37
     éléments
    0.37
    ineuses
    0.37
     Oberfläche
    0.36
     Tamaño
    0.36
    POSITIVE LOGITS
    ा
    0.39
    ↵↵
    0.39
    ↵
    0.35
     reorganization
    0.33
     trad
    0.32
     할
    0.32
     landsc
    0.32
     trivia
    0.32
     photography
    0.31
     sust
    0.31
    Act Density 0.540%

    No Known Activations