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

    Neuronpedia

    INDEX
    Explanations

    document templates and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oubtedly
    0.42
    Understand
    0.39
    ากหลาย
    0.38
    ම
    0.37
    लेषण
    0.36
     whatnot
    0.35
    在這個
    0.35
    :'',
    0.34
    வ்வேறு
    0.34
    рина
    0.34
    POSITIVE LOGITS
    </h3>
    0.44
     USA
    0.42
    </h2>
    0.42
     KIA
    0.38
     US
    0.38
     BA
    0.37
     www
    0.37
     AWS
    0.37
     FULL
    0.37
     Simple
    0.37
    Act Density 0.018%

    No Known Activations