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

    Neuronpedia

    INDEX
    Explanations

    wave function collapse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     móc
    0.39
    Churn
    0.37
    imread
    0.37
     churn
    0.35
     ascended
    0.34
     લી
    0.34
    捎
    0.34
     diatomic
    0.34
     Innoc
    0.34
     CRUIS
    0.34
    POSITIVE LOGITS
     collapse
    2.47
     collapses
    2.33
     collapsed
    2.25
     collapsing
    2.20
    collapse
    2.09
     Collapse
    2.05
    Collapse
    1.98
    坍
    1.87
    collapsed
    1.77
    塌
    1.61
    Act Density 0.017%

    No Known Activations