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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TRX
    0.64
    ્ન
    0.61
     något
    0.59
     मजब
    0.56
     IHC
    0.56
    říve
    0.56
    ന്തു
    0.55
     असे
    0.55
     soddisf
    0.54
     ತ
    0.53
    POSITIVE LOGITS
    python
    0.75
    java
    0.71
    Java
    0.68
    Python
    0.67
     python
    0.64
     java
    0.63
     programming
    0.61
     TypeScript
    0.58
    नाडा
    0.58
    JAVA
    0.57
    Act Density 0.154%

    No Known Activations