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

    Neuronpedia

    INDEX
    Explanations

    weather, Tropics, erotic novel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.04
    t
    1.03
    y
    1.00
    ের
    0.98
    न
    0.87
    س
    0.86
    م
    0.83
    tional
    0.82
    tive
    0.82
    د
    0.81
    POSITIVE LOGITS
     fleste
    0.47
    𝒂
    0.46
     través
    0.46
     mysterious
    0.41
    ѕ
    0.41
     البته
    0.41
     Todo
    0.41
    btnInventory
    0.41
     pharma
    0.40
     aforementioned
    0.40
    Act Density 15.601%

    No Known Activations