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

    Neuronpedia

    INDEX
    Explanations

    food and wellness terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ol
    1.23
    us
    1.17
    ar
    0.92
    ang
    0.92
    ina
    0.91
    ong
    0.90
    ing
    0.89
    el
    0.88
    é
    0.83
    ai
    0.83
    POSITIVE LOGITS
    ↵↵
    1.04
    </h2>
    0.96
    ↵
    0.84
    </h3>
    0.83
    我
    0.80
    ために
    0.75
     dobr
    0.73
     frio
    0.71
    </h4>
    0.70
     Primeiro
    0.69
    Act Density 0.060%

    No Known Activations