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

    Neuronpedia

    INDEX
    Explanations

    harder or damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormData
    0.45
     року
    0.45
    atmosphère
    0.44
    carboxylic
    0.43
    蒎
    0.43
    ření
    0.43
    țiile
    0.42
    ət
    0.42
     lavage
    0.42
    hā
    0.42
    POSITIVE LOGITS
     hedge
    0.40
     उद्यम
    0.40
     Infrastructure
    0.38
     Hedge
    0.38
     Tracks
    0.37
    ；
    0.37
     इज
    0.37
     नेतृत्व
    0.37
     Husky
    0.37
     تعلم
    0.37
    Act Density 0.004%

    No Known Activations