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

    Neuronpedia

    INDEX
    Explanations

    meantime, here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    নেল
    0.43
    決して
    0.42
     kein
    0.40
     znaleźć
    0.38
     nėra
    0.36
     değildir
    0.36
     ciel
    0.35
    (_.
    0.35
    詳しい
    0.35
     sním
    0.35
    POSITIVE LOGITS
     let
    0.95
     here
    0.82
     Let
    0.82
    Let
    0.82
    Here
    0.78
     Here
    0.77
     Voici
    0.74
    让我
    0.71
     lets
    0.70
    Voici
    0.70
    Act Density 0.017%

    No Known Activations