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

    Neuronpedia

    INDEX
    Explanations

    ends with 'st' or 'ist'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আওয়ামীলীগের
    0.38
     दोषी
    0.38
     anges
    0.36
     outrageous
    0.35
    àng
    0.35
    ild
    0.35
    zem
    0.35
    čke
    0.34
    iente
    0.33
    itatis
    0.33
    POSITIVE LOGITS
    ்ட
    0.75
    ructions
    0.64
    aurant
    0.64
    rategy
    0.57
    навли
    0.57
    rations
    0.57
    aurants
    0.57
    hetics
    0.55
    ндарт
    0.55
    ካከል
    0.54
    Act Density 0.055%

    No Known Activations