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

    Neuronpedia

    INDEX
    Explanations

    public java code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (#
    0.85
     nullptr
    0.81
    nullptr
    0.76
    #:
    0.74
    #.
    0.73
    #
    0.72
     crouching
    0.72
    (#
    0.70
     #
    0.70
     cisplatin
    0.68
    POSITIVE LOGITS
    boolean
    2.17
    String
    2.08
     boolean
    2.00
     String
    1.98
    final
    1.85
     final
    1.83
    Integer
    1.43
    java
    1.39
    Object
    1.35
    StringBuffer
    1.34
    Act Density 0.130%

    No Known Activations