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

    Neuronpedia

    INDEX
    Explanations

    quantum objects, typical starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    隶
    0.43
    ánico
    0.43
    下記の
    0.40
    🌂
    0.40
    下图
    0.40
     सुपारी
    0.40
    西北
    0.39
     Balliye
    0.38
    <unused2141>
    0.38
    服務
    0.38
    POSITIVE LOGITS
     f
    0.41
     hard
    0.41
    ബന്ധ
    0.41
     Disney
    0.40
    Disney
    0.38
     math
    0.38
     mild
    0.38
    ++,
    0.38
     comfort
    0.37
     trained
    0.37
    Act Density 0.000%

    No Known Activations