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

    Neuronpedia

    INDEX
    Explanations

    SQL JOIN ON conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stag
    0.39
     মিয়া
    0.37
    融资
    0.37
     steels
    0.36
    ستی
    0.35
     Pét
    0.35
     STEEL
    0.35
    новні
    0.35
     Pipe
    0.35
     connues
    0.34
    POSITIVE LOGITS
     partitions
    0.39
     Partition
    0.38
    kari
    0.36
     Caste
    0.35
    psum
    0.34
    ''.
    0.34
    扣
    0.33
     técn
    0.33
    StateException
    0.33
    Partition
    0.33
    Act Density 0.001%

    No Known Activations