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

    Neuronpedia

    INDEX
    Explanations

    expressing strong emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    valley
    0.53
    캇
    0.51
     ﺍﻟ
    0.50
    ież
    0.50
     carinatis
    0.48
     ಉಪಯೋಗ
    0.47
     территория
    0.46
    𝓾
    0.46
    出す
    0.46
     ଏ
    0.46
    POSITIVE LOGITS
     Heroes
    0.51
     Speak
    0.47
    ق
    0.47
    רו
    0.47
    缺乏
    0.46
     Critics
    0.46
    绍
    0.46
     Solid
    0.45
     Hero
    0.45
     Image
    0.45
    Act Density 0.001%

    No Known Activations