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

    Neuronpedia

    INDEX
    Explanations

    java class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arched
    0.40
    绡
    0.40
     kinematic
    0.38
    土壤
    0.37
     aminoglycos
    0.37
    萜
    0.37
     بیگ
    0.37
    圯
    0.37
    辐射
    0.36
    㿟
    0.36
    POSITIVE LOGITS
    StringBuilder
    0.48
     IntelliJ
    0.42
     FXMLLoader
    0.40
    Gson
    0.40
    String
    0.38
     JOptionPane
    0.38
    requireNonNull
    0.37
    Thread
    0.37
    LocalDateTime
    0.37
    ni
    0.36
    Act Density 0.004%

    No Known Activations