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

    Neuronpedia

    INDEX
    Explanations

    API access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మంత్రి
    0.47
     شہری
    0.46
     একটী
    0.46
    propan
    0.45
    bromo
    0.45
     bicarbon
    0.45
     hamil
    0.45
    ENDMENT
    0.44
     parlament
    0.43
    zneim
    0.43
    POSITIVE LOGITS
    格
    0.46
    ファ
    0.46
    ↵
    0.43
    }}
    0.43
    前
    0.42
    atique
    0.42
    一次
    0.42
    </
    0.42
     اقتص
    0.41
    離
    0.41
    Act Density 0.001%

    No Known Activations