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

    Neuronpedia

    INDEX
    Explanations

    naming catchy names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    物体
    0.43
     intolerance
    0.41
     симпто
    0.41
    \{(
    0.41
     ধৈ
    0.41
     situatie
    0.40
     $\{(
    0.40
     تحدث
    0.40
     解説
    0.39
     relief
    0.39
    POSITIVE LOGITS
     naming
    1.14
     names
    1.09
     catchy
    1.09
     evocative
    1.01
     nicknames
    0.97
     name
    0.97
     moniker
    0.95
     branding
    0.94
    Naming
    0.94
    naming
    0.93
    Act Density 0.132%

    No Known Activations