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

    Neuronpedia

    INDEX
    Explanations

    ```bash```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ይታ
    0.92
     verbs
    0.91
    ὴ
    0.91
    فران
    0.87
     vowels
    0.87
    ᥱ
    0.87
    ፥
    0.86
    ,]$
    0.86
     groovy
    0.85
     metaf
    0.85
    POSITIVE LOGITS
    」
    0.79
    rzed
    0.74
     काही
    0.73
     वेळ
    0.72
     zuvor
    0.72
     здійсню
    0.71
     продовжу
    0.71
    )
    0.70
    romad
    0.70
    Leben
    0.69
    Act Density 0.026%

    No Known Activations