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

    Neuronpedia

    INDEX
    Explanations

    able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ที่จะ
    0.75
    被
    0.73
     být
    0.70
    ToBe
    0.67
     быть
    0.65
     被
    0.64
     być
    0.60
    而被
    0.57
     being
    0.56
    ถูก
    0.55
    POSITIVE LOGITS
    芗
    0.38
    arena
    0.36
     mai
    0.35
     acog
    0.35
     Mai
    0.34
    amay
    0.34
    Herald
    0.34
     fath
    0.34
     inheritance
    0.33
    arik
    0.33
    Act Density 0.025%

    No Known Activations