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

    Neuronpedia

    INDEX
    Explanations

    stops or diminishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     മികച്ച
    0.46
    帮你
    0.43
     bättre
    0.42
    ﻩ
    0.41
     лучше
    0.40
     ఏర్
    0.40
     บวก
    0.40
    ൊരു
    0.39
     بہتر
    0.39
     አማ
    0.39
    POSITIVE LOGITS
     diminished
    1.07
    失去了
    1.06
     decreased
    1.00
     reduced
    0.96
     loses
    0.96
    失去
    0.91
     perder
    0.88
     lose
    0.87
     переста
    0.86
     mất
    0.84
    Act Density 0.301%

    No Known Activations