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

    Neuronpedia

    INDEX
    Explanations

    diagram syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     финансо
    0.55
    ihanna
    0.51
    ghan
    0.48
    Aku
    0.48
    ahy
    0.48
    ксана
    0.48
    មិន
    0.47
    coran
    0.47
     soirée
    0.46
    😩
    0.46
    POSITIVE LOGITS
     diagram
    0.82
     Diagram
    0.80
     arrows
    0.73
    Diagram
    0.73
     diagrams
    0.71
     arrow
    0.68
     Diagrams
    0.66
     subgraph
    0.65
     nodes
    0.65
     vertices
    0.64
    Act Density 0.111%

    No Known Activations