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

    Neuronpedia

    INDEX
    Explanations

    was acting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tar
    0.52
    fl
    0.52
     lakes
    0.49
    oo
    0.49
    ጆች
    0.49
    notebook
    0.48
    SA
    0.48
    chlor
    0.47
    currentNode
    0.47
    늦
    0.47
    POSITIVE LOGITS
     पारिवारिक
    0.45
    شی
    0.45
     differences
    0.44
     नवीन
    0.44
     семей
    0.44
     livré
    0.43
     diferença
    0.43
     diálogo
    0.42
     glimmer
    0.42
     gương
    0.42
    Act Density 0.000%

    No Known Activations