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

    Neuronpedia

    INDEX
    Explanations

    I'm not sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ান্তরিত
    0.82
     GUID
    0.75
     airlift
    0.73
    しく
    0.70
     പോലും
    0.70
    uu
    0.69
     COR
    0.66
    のある
    0.66
    らが
    0.66
    ڈین
    0.66
    POSITIVE LOGITS
    fungsi
    0.76
    for
    0.74
    तमंद
    0.74
    其他
    0.71
    staaten
    0.71
     اخرى
    0.70
     rappresenta
    0.70
    вро
    0.69
     ovvero
    0.68
     інші
    0.68
    Act Density 0.002%

    No Known Activations