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

    Neuronpedia

    INDEX
    Explanations

    principles and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    द्वीप
    0.43
     ativa
    0.40
     nyc
    0.40
    nesses
    0.40
    úsica
    0.40
     zorunda
    0.39
    nego
    0.39
    ニ
    0.39
    party
    0.38
     бала
    0.38
    POSITIVE LOGITS
     اصول
    0.44
    Principles
    0.42
     विल
    0.40
    헌
    0.39
    筋
    0.39
    代
    0.38
     principles
    0.38
     عنصر
    0.38
    ပို့
    0.37
     ප්‍රති
    0.37
    Act Density 0.003%

    No Known Activations