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

    Neuronpedia

    INDEX
    Explanations

    lists of programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    leda
    0.41
    jelen
    0.40
     Bells
    0.37
    jik
    0.37
    رو
    0.37
     jewels
    0.36
    JDK
    0.36
    java
    0.36
    jed
    0.36
    flush
    0.36
    POSITIVE LOGITS
     EE
    0.51
     bytecode
    0.46
     ee
    0.44
     supercritical
    0.44
    पालन
    0.42
     phenytoin
    0.42
    EE
    0.42
     ಸುಮ
    0.41
     वर्चुअल
    0.39
    虚拟机
    0.39
    Act Density 0.007%

    No Known Activations