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

    Neuronpedia

    INDEX
    Explanations

    yourself or others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    0.43
     volunt
    0.41
    দায়িক
    0.39
     personally
    0.39
     willfully
    0.38
     Hing
    0.38
     doo
    0.38
     environmental
    0.37
     delic
    0.37
     stella
    0.37
    POSITIVE LOGITS
     BLUENRG
    0.40
    }=(\
    0.39
    PROVIDED
    0.38
     proporcionan
    0.38
     జాగ
    0.38
    勺
    0.36
    ται
    0.36
     स्कीम
    0.36
     свою
    0.35
    že
    0.35
    Act Density 0.012%

    No Known Activations