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

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suggestions
    0.43
    ╼
    0.41
    JobList
    0.41
    કમ
    0.40
    "})
    0.40
    也将
    0.39
    suggestions
    0.39
     subcommand
    0.38
     במ
    0.38
     tranquila
    0.38
    POSITIVE LOGITS
    need
    0.60
     necesitamos
    0.60
     need
    0.59
     ஏன்
    0.59
     behö
    0.54
     precisamos
    0.54
     NEED
    0.52
     Importance
    0.51
     necesitas
    0.51
     needed
    0.51
    Act Density 0.103%

    No Known Activations