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

    Neuronpedia

    INDEX
    Explanations

    mentioned, specific, or descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.50
    7
    0.49
    9
    0.46
    8
    0.44
    或
    0.44
    1
    0.43
     或
    0.42
    2
    0.42
    5
    0.42
    3
    0.41
    POSITIVE LOGITS
     appunto
    0.44
     مذکور
    0.42
     dispositif
    0.41
     aforementioned
    0.41
     matchup
    0.38
     festa
    0.38
     उक्त
    0.38
     intensidad
    0.37
     disequ
    0.37
     confertim
    0.37
    Act Density 0.842%

    No Known Activations