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

    Neuronpedia

    INDEX
    Explanations

    i'd love to hear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.61
     wickets
    0.59
    s
    0.59
     u
    0.59
     sensations
    0.58
     d
    0.57
     wizards
    0.57
     concess
    0.55
    colored
    0.54
     с
    0.54
    POSITIVE LOGITS
    Thermal
    0.53
    وكب
    0.52
    Economic
    0.51
    OOP
    0.51
    Structural
    0.51
    寤
    0.50
    Redis
    0.50
    Lewis
    0.49
    ికె
    0.49
    щины
    0.48
    Act Density 0.001%

    No Known Activations