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

    Neuronpedia

    INDEX
    Explanations

    if, but, or even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mują
    0.45
     Automobiles
    0.43
     தனி
    0.41
    頎
    0.40
    ases
    0.40
     మన
    0.40
    ቼ
    0.39
    ettel
    0.39
    ल्पन
    0.38
    个人
    0.38
    POSITIVE LOGITS
    0.45
              
    0.40
     کیونکہ
    0.39
     çünkü
    0.38
     stigmat
    0.37
    “)
    0.37
    0.37
     totiž
    0.36
               
    0.35
    即便
    0.34
    Act Density 0.014%

    No Known Activations