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

    Neuronpedia

    INDEX
    Explanations

    basic, derivatives, forces, roll, optimistic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    传
    0.52
    慧
    0.48
    วน
    0.45
    你会
    0.43
    驾
    0.42
    专门
    0.41
    一旦
    0.41
    西亚
    0.41
    눔
    0.40
    PropertySheets
    0.40
    POSITIVE LOGITS
     der
    0.46
     hind
    0.46
     abrasion
    0.45
     direção
    0.45
     barred
    0.44
     neoliberal
    0.44
     mountain
    0.43
     paž
    0.43
     una
    0.43
    lichen
    0.43
    Act Density 0.001%

    No Known Activations