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

    Neuronpedia

    INDEX
    Explanations

    utf-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     medium
    0.50
     Medium
    0.50
     मीडियम
    0.43
     mediums
    0.42
    medium
    0.41
     solicitor
    0.41
     Gresham
    0.40
     MEDIUM
    0.39
    Medium
    0.38
    MEDIUM
    0.38
    POSITIVE LOGITS
    ensch
    0.44
    latin
    0.38
     한국
    0.36
    ods
    0.35
    ^{-
    0.35
     পার্শ্ব
    0.35
    JScripts
    0.34
     혹
    0.34
    Malay
    0.34
    нями
    0.34
    Act Density 0.000%

    No Known Activations