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

    Neuronpedia

    INDEX
    Explanations

    say "/"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حتی
    0.50
     cualquier
    0.50
     bijvoorbeeld
    0.48
     gibi
    0.47
     kahit
    0.46
     или
    0.46
    ….
    0.46
    மற்ற
    0.46
     thậm
    0.46
     അല്ലെങ്കിൽ
    0.45
    POSITIVE LOGITS
    /**
    0.50
    Overview
    0.50
     Overview
    0.49
    /***
    0.49
    ultimate
    0.46
     Defining
    0.45
    summary
    0.44
    Summary
    0.44
    scenario
    0.44
     Methodology
    0.44
    Act Density 0.255%

    No Known Activations