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

    Neuronpedia

    INDEX
    Explanations

    enforcement, enforceable, unenforceable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possesses
    0.35
     terdapat
    0.34
     possui
    0.34
     består
    0.33
     mutta
    0.33
     besteht
    0.33
     besitzt
    0.33
     possuem
    0.32
     predefined
    0.31
     intermediate
    0.31
    POSITIVE LOGITS
     కూడా
    0.39
    숴
    0.36
    ख्ती
    0.36
     делать
    0.35
    addKill
    0.33
    ्‍यादा
    0.33
     enforcement
    0.33
    телям
    0.33
     enforceable
    0.32
     unenforceable
    0.32
    Act Density 0.000%

    No Known Activations