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

    Neuronpedia

    INDEX
    Explanations

    JavaScript

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diversión
    0.39
     distributes
    0.38
     loi
    0.38
     vacanam
    0.38
    будь
    0.37
     борьбе
    0.37
    티브
    0.37
    manha
    0.36
     distribución
    0.36
     জারি
    0.36
    POSITIVE LOGITS
    alive
    0.39
     half
    0.38
     CSE
    0.37
    Plant
    0.37
    ص
    0.37
    Charter
    0.37
    ikt
    0.37
     Gunnar
    0.36
     Charcoal
    0.36
    ओके
    0.35
    Act Density 0.002%

    No Known Activations