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

    Neuronpedia

    INDEX
    Explanations

    positive interaction and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الضرب
    0.34
    ock
    0.33
     tackles
    0.33
    癢
    0.32
     centroids
    0.32
     עצ
    0.32
     پھیل
    0.32
    Bes
    0.32
    RGB
    0.31
     nozzles
    0.31
    POSITIVE LOGITS
     interaction
    1.81
     interactions
    1.81
     interacting
    1.71
     relationship
    1.70
     interact
    1.69
     interacted
    1.67
     interacción
    1.64
     interação
    1.63
     interacts
    1.61
     Interactions
    1.59
    Act Density 0.061%

    No Known Activations