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

    Neuronpedia

    INDEX
    Explanations

    command piping languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destruir
    1.07
    ڈیو
    1.06
    alunos
    1.00
    AllWindows
    0.99
     comum
    0.96
     comuns
    0.94
    គឺជា
    0.94
    tudo
    0.94
     membros
    0.93
     iniciar
    0.93
    POSITIVE LOGITS
     ép
    0.96
     ó
    0.89
    LIMIT
    0.80
     ná
    0.73
     straw
    0.70
    瀘
    0.69
    Gran
    0.68
    separate
    0.68
     nes
    0.68
    ^\
    0.68
    Act Density 0.034%

    No Known Activations