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

    Neuronpedia

    INDEX
    Explanations

    val, gart, fra, med, vol, ഹ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੁ
    0.32
    是
    0.32
    凭
    0.31
    给人
    0.30
     اتار
    0.29
     চাঁদপুর
    0.29
    指出
    0.28
     الجزائر
    0.28
    偪
    0.28
    佗
    0.28
    POSITIVE LOGITS
     in
    0.35
    /-
    0.32
     for
    0.30
     vulnerability
    0.30
    ষ্টা
    0.30
     cycles
    0.30
    1
    0.30
    ل
    0.29
    7
    0.29
     cons
    0.29
    Act Density 0.037%

    No Known Activations