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

    Neuronpedia

    INDEX
    Explanations

    Ford car models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    1.88
    <0xB0>
    1.86
    ዻ
    1.86
    ਗ
    1.75
    <0xA1>
    1.73
    ্দ্র
    1.70
    ы
    1.70
    밥
    1.69
    데
    1.68
    𒁕
    1.68
    POSITIVE LOGITS
    ian
    2.33
    yce
    2.20
    ین
    2.00
     quelconque
    1.99
    ่า
    1.91
    köz
    1.91
    ো
    1.91
    ite
    1.86
    ̣i
    1.84
    ure
    1.82
    Act Density 0.001%

    No Known Activations