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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verbs
    0.54
    ђено
    0.52
    ্ু
    0.52
    জন্য
    0.49
    خود
    0.49
    ванович
    0.48
     ομά
    0.47
    倰
    0.47
    دیا
    0.46
    േരി
    0.46
    POSITIVE LOGITS
     Invest
    0.55
     Commission
    0.50
     Mutant
    0.48
     N
    0.46
     Game
    0.46
     Sport
    0.46
    -
    0.46
    ↵
    0.45
     ned
    0.44
     Story
    0.44
    Act Density 0.002%

    No Known Activations