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

    Neuronpedia

    INDEX
    Explanations

    .io

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    放到
    -0.07
    xing
    -0.07
     SECURITY
    -0.07
    笑着说
    -0.07
     Swedish
    -0.07
    RID
    -0.07
    黠
    -0.07
     ek
    -0.06
     уд
    -0.06
     MIL
    -0.06
    POSITIVE LOGITS
    (encoded
    0.08
    .comm
    0.07
    直观
    0.07
    쫏
    0.07
     Comm
    0.06
    摘要
    0.06
    ان
    0.06
    ‾
    0.06
    茳
    0.06
    Andre
    0.06
    Act Density 0.000%

    No Known Activations