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

    Neuronpedia

    INDEX
    Explanations

    air volume, wall erected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aio
    1.83
     wits
    1.76
    queued
    1.73
    𝐭
    1.73
    wif
    1.72
    𝐦
    1.69
    argc
    1.68
    m
    1.66
    𝐟
    1.62
    این
    1.60
    POSITIVE LOGITS
    не
    1.54
     दिसंबर
    1.50
     викона
    1.45
    モバイル
    1.41
     drawbacks
    1.40
    чих
    1.40
     bushy
    1.39
     pessoal
    1.38
    كل
    1.35
    Д
    1.34
    Act Density 0.000%

    No Known Activations