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

    Neuronpedia

    INDEX
    Explanations

    New York City

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ோது
    0.91
     对象
    0.86
     গেরিলাদের
    0.85
     கூடிய
    0.85
    ၟ
    0.84
    <bos>
    0.83
     durée
    0.81
    apay
    0.81
    犷
    0.81
    lings
    0.80
    POSITIVE LOGITS
     mediate
    1.01
     pierced
    0.96
    י
    0.93
    ต์
    0.89
     custod
    0.88
    ম
    0.88
    ை
    0.88
    ਹੀਂ
    0.87
     decon
    0.86
     ranked
    0.86
    Act Density 0.000%

    No Known Activations