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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (visible
    -0.07
    組織
    -0.07
     sufficient
    -0.07
     failures
    -0.07
    (rep
    -0.06
     inspired
    -0.06
    erville
    -0.06
    芯片
    -0.06
    missible
    -0.06
    (tf
    -0.06
    POSITIVE LOGITS
     Extended
    0.07
    废旧
    0.07
     SOLD
    0.07
     Pública
    0.07
    SAVE
    0.07
     income
    0.07
     =>↵
    0.06
    مراك
    0.06
    '],['
    0.06
    &);↵↵
    0.06
    Act Density 0.039%

    No Known Activations