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

    Neuronpedia

    INDEX
    Explanations

    lots, plenty, huge amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Though
    0.43
    是一
    0.38
    是不
    0.38
    Theorem
    0.36
    etc
    0.36
     )
    0.35
    するのは
    0.35
     etc
    0.35
    .)
    0.34
     :
    0.34
    POSITIVE LOGITS
     lots
    0.73
    lots
    0.56
    Lots
    0.50
     প্রচুর
    0.50
     plenty
    0.49
    많은
    0.47
     huge
    0.47
     tons
    0.47
    大きな
    0.46
     высокая
    0.45
    Act Density 0.082%

    No Known Activations