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

    Neuronpedia

    INDEX
    Explanations

    chaos energy, cơ hội

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভাঙ
    0.41
     tão
    0.38
    άσ
    0.38
    🦯
    0.38
    ưu
    0.37
     мор
    0.37
    Devices
    0.36
    Humidity
    0.36
    PathVariable
    0.36
     নু
    0.36
    POSITIVE LOGITS
     specialist
    0.48
    reward
    0.47
    ments
    0.43
     reward
    0.43
    sele
    0.42
     اسمها
    0.42
     ment
    0.41
     Habsburg
    0.41
     reg
    0.40
     re
    0.39
    Act Density 0.000%

    No Known Activations