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

    Neuronpedia

    INDEX
    Explanations

    Integer, String, ancient types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Burberry
    0.50
     seafood
    0.49
     Bangkok
    0.49
     crime
    0.48
     Miami
    0.47
     Tây
    0.46
     Mississippi
    0.46
     Mumbai
    0.46
     Cuc
    0.45
     KFC
    0.45
    POSITIVE LOGITS
    砟
    0.52
    Gradle
    0.50
    Remote
    0.49
    SystemCall
    0.48
    ssystem
    0.48
     ఆదేశ
    0.48
    Alumno
    0.47
    ވ
    0.46
    堭
    0.46
    plemente
    0.46
    Act Density 0.006%

    No Known Activations