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

    Neuronpedia

    INDEX
    Explanations

    DB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    with
    -0.07
     workers
    -0.07
     From
    -0.07
     choir
    -0.07
    nger
    -0.07
     When
    -0.07
     bombs
    -0.07
     tenant
    -0.06
     brighter
    -0.06
     scales
    -0.06
    POSITIVE LOGITS
    心理
    0.08
    .site
    0.07
     frost
    0.06
    дан
    0.06
     v�
    0.06
    兰
    0.06
    手机号
    0.06
    тою
    0.06
    
    0.06
    .getMinutes
    0.06
    Act Density 0.210%

    No Known Activations