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

    Neuronpedia

    INDEX
    Explanations

    abilities and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     መጠን
    0.49
     cognizant
    0.45
     abolish
    0.44
     mobilize
    0.44
     சித்தர்
    0.42
    ，「
    0.41
     создавать
    0.41
     व्हिडी
    0.41
    助于
    0.41
     समक्ष
    0.40
    POSITIVE LOGITS
     was
    0.51
     had
    0.49
     has
    0.47
    required
    0.45
     hatte
    0.45
     یک
    0.42
    has
    0.41
    was
    0.41
     eine
    0.40
     Fläche
    0.40
    Act Density 0.069%

    No Known Activations