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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inches
    -0.07
    CONTEXT
    -0.06
    mium
    -0.06
     Grove
    -0.06
    ADS
    -0.06
    ocaly
    -0.06
     poem
    -0.06
     Odin
    -0.06
    dds
    -0.06
    ASTE
    -0.06
    POSITIVE LOGITS
    备
    0.07
    まだ
    0.06
     america
    0.06
     retreated
    0.06
    批
    0.06
    .FileSystem
    0.06
    
    0.06
     Artists
    0.06
    客户
    0.06
     prioritize
    0.06
    Act Density 0.037%

    No Known Activations