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

    Neuronpedia

    INDEX
    Explanations

    established meaning, commitment history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    og
    0.82
     $\
    0.79
    ا
    0.77
    </tr>
    0.76
    ↵
    0.75
    t
    0.74
      
    0.71
    ong
    0.71
    T
    0.71
    it
    0.69
    POSITIVE LOGITS
    স্থানে
    0.91
    িনবার্গ
    0.91
     sparsebundle
    0.89
     totiž
    0.88
     LPTMR
    0.87
     anabolic
    0.87
    lastCursor
    0.86
     bhav
    0.84
    প্যাথ
    0.84
     bowiem
    0.84
    Act Density 0.001%

    No Known Activations