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

    Neuronpedia

    INDEX
    Explanations

    list items and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    motivated
    0.65
     principes
    0.60
     Xinhua
    0.59
    interacting
    0.59
     도입
    0.58
     reproducible
    0.57
     conceitos
    0.56
    inspired
    0.56
    conceptual
    0.56
    norr
    0.56
    POSITIVE LOGITS
     listed
    1.51
     listing
    1.45
     category
    1.39
     dropdown
    1.35
     Listed
    1.31
     listings
    1.29
     list
    1.23
     Listing
    1.23
     lists
    1.23
    Listed
    1.18
    Act Density 0.690%

    No Known Activations