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

    Neuronpedia

    INDEX
    Explanations

    process outline

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Legislation
    0.51
     Políticas
    0.50
     Announces
    0.50
     Dateien
    0.49
     Objekte
    0.48
     Details
    0.46
     Requirements
    0.46
     Einstellungen
    0.46
     Möglichkeiten
    0.46
     Principles
    0.45
    POSITIVE LOGITS
     albeit
    0.70
    albeit
    0.64
     piece
    0.63
     set
    0.62
     sense
    0.61
     approach
    0.58
    izable
    0.58
     yet
    0.57
     amount
    0.57
     outpouring
    0.56
    Act Density 1.447%

    No Known Activations