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

    Neuronpedia

    INDEX
    Explanations

    Option 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concerts
    0.42
     lawsuits
    0.40
     debate
    0.39
     relatos
    0.39
     diskusi
    0.36
     debates
    0.35
     balo
    0.35
     stories
    0.34
    வல
    0.34
     એપ્
    0.33
    POSITIVE LOGITS
    example
    0.38
    סה
    0.38
    这个人
    0.36
     فهي
    0.36
     below
    0.35
    Example
    0.35
     Below
    0.35
    เต็ม
    0.35
    tem
    0.34
    这是一
    0.34
    Act Density 0.284%

    No Known Activations