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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Re
    -0.07
     अर्थात
    -0.07
     दक्ष
    -0.07
     базы
    -0.07
    .Positive
    -0.07
    ET
    -0.07
    iera
    -0.07
     attempted
    -0.07
    August
    -0.07
    SA
    -0.07
    POSITIVE LOGITS
     Conversations
    0.09
     campeonato
    0.08
     FHA
    0.08
     creë
    0.08
     پنج
    0.08
    帖子
    0.08
     Cupertino
    0.08
     રોક
    0.08
     kamers
    0.08
    พัก
    0.08
    Act Density 0.001%

    No Known Activations