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

    Neuronpedia

    INDEX
    Explanations

    listing pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或
    0.40
    หรือ
    0.40
    чить
    0.39
    度和
    0.38
    UP
    0.38
    нили
    0.38
    вили
    0.37
    живання
    0.37
    하다
    0.36
    дон
    0.36
    POSITIVE LOGITS
     Dieses
    0.46
     poiché
    0.45
     certes
    0.44
     Apesar
    0.44
     sicherlich
    0.43
     puisque
    0.43
     ponieważ
    0.43
     apesar
    0.43
     பல்வேறு
    0.42
     Wszyst
    0.41
    Act Density 0.029%

    No Known Activations