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

    Neuronpedia

    INDEX
    Explanations

    entity-description pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‹
    0.48
     +/-
    0.48
     rapidez
    0.47
    께
    0.46
     Mme
    0.46
     jalap
    0.46
     ovoj
    0.45
     délais
    0.45
    禮
    0.44
    ന്‍റെ
    0.44
    POSITIVE LOGITS
     Wikipedia
    0.66
     /ˈ
    0.64
     Wikimedia
    0.63
    ,[
    0.60
    ː
    0.59
    Wikimedia
    0.58
    United
    0.56
    Wikipedia
    0.54
     United
    0.54
    .[
    0.54
    Act Density 0.273%

    No Known Activations