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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Legislation
    0.54
     Stuff
    0.52
    Stuff
    0.47
     Evidence
    0.47
     Mga
    0.44
     Equipment
    0.43
     Advice
    0.43
     Các
    0.43
    legislation
    0.42
    Evidence
    0.41
    POSITIVE LOGITS
     kinds
    0.52
     pesky
    0.48
     guys
    0.47
     particular
    0.47
     machines
    0.46
     conversations
    0.45
     folks
    0.45
     videos
    0.44
     examples
    0.44
     days
    0.44
    Act Density 0.419%

    No Known Activations