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

    Neuronpedia

    INDEX
    Explanations

    Here's why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wondered
    0.53
     famosos
    0.45
     wellknown
    0.45
     anlamına
    0.43
     ünlü
    0.43
     eksper
    0.42
     origins
    0.41
     учены
    0.41
    ásticas
    0.41
     extracts
    0.41
    POSITIVE LOGITS
    我认为
    0.64
     Ultimately
    0.54
    আমার
    0.54
     Putting
    0.52
     Others
    0.51
    Adding
    0.51
    理由
    0.50
    मुझे
    0.50
    Putting
    0.50
     других
    0.50
    Act Density 0.001%

    No Known Activations