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

    Neuronpedia

    INDEX
    Explanations

    stipulates, stipulated, accomplished

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🍐
    0.67
    SEED
    0.56
    <unused1723>
    0.55
    External
    0.55
     Política
    0.54
    त्य
    0.54
    Oz
    0.53
    Rod
    0.53
    Harmony
    0.53
    Pr
    0.52
    POSITIVE LOGITS
     stipulates
    0.94
     می‌باشد
    0.85
     stipulated
    0.83
     accomplished
    0.80
     hereby
    0.79
     andare
    0.78
     undertake
    0.78
     mempunyai
    0.78
     utilisé
    0.78
     donnent
    0.78
    Act Density 0.692%

    No Known Activations