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

    Neuronpedia

    INDEX
    Explanations

    worry and anticipation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ange
    0.43
     delimiter
    0.42
     obese
    0.42
     squeezed
    0.40
     tri
    0.40
     diarrhea
    0.40
     upwards
    0.40
     tir
    0.38
     Diamond
    0.38
     squeeze
    0.38
    POSITIVE LOGITS
     도전
    0.44
    风险
    0.43
    㥳
    0.43
    學習
    0.42
    䄳
    0.42
    夗
    0.41
    学习
    0.41
     معروف
    0.40
     portefeuille
    0.39
    珬
    0.39
    Act Density 0.000%

    No Known Activations