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

    Neuronpedia

    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     honda
    -0.07
     consectetur
    -0.07
    .UTC
    -0.07
    ⚙
    -0.07
     输出
    -0.07
    MMdd
    -0.07
    宠
    -0.07
    "id
    -0.07
     Philips
    -0.07
    鸠
    -0.07
    POSITIVE LOGITS
    ONENT
    0.07
     form
    0.06
    =date
    0.06
    扭曲
    0.06
    клад
    0.06
    (history
    0.06
    ਯ
    0.06
    正因为
    0.06
    】
    0.06
    }}
    0.06
    Act Density 0.000%

    No Known Activations