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

    Neuronpedia

    INDEX
    Explanations

    unified transit and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کوئی
    0.40
     Cliff
    0.40
     Rea
    0.39
     Ram
    0.38
     Standort
    0.38
     sırada
    0.38
     Personnel
    0.37
     Chem
    0.36
     setback
    0.36
     Pel
    0.36
    POSITIVE LOGITS
     heps
    0.45
     提供
    0.44
    舞
    0.43
    提供
    0.42
    ATION
    0.41
     ಏ
    0.41
    īd
    0.41
     orchestras
    0.40
     intuitive
    0.40
     นั่น
    0.40
    Act Density 0.001%

    No Known Activations